lanolin

noun 2 senses

a yellow viscous animal oil extracted from wool; a mixture of fatty acids and esters; used in some ointments and cosmetics

English Español Français ラノリン 羊毛脂
Qwen3 8B
DeepSeek V3
Mistral 7B

Panels 3, 4 and 5 are computed per model. Switch to see them disagree.

1 Your word measured
noun 2 senses 2 synonyms

Definitions come from WordNet, a hand-curated dictionary.

2 To an AI, it's pieces measured
DeepSeek V3 l anol in 3 tokens
Mistral 7B lan olin 2 tokens
Qwen3 8B lan olin 2 tokens

This is the tokenizer splitting text, not the model understanding it.

3 Synonyms, antonyms, and the AI measured
Qwen3 8B
DeepSeek V3
Mistral 7B

This model splits lanolin into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

Shade shows how close the model puts each word to lanolin. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.

This model splits lanolin into 3 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

Dictionary synonyms measured

wool fat wool grease

Shade shows how close the model puts each word to lanolin. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.

This model splits lanolin into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

Shade shows how close the model puts each word to lanolin. 0 of 2 dictionary synonyms are in this build; the rest have no vector to compare yet.

Model neighbours are distributional, not dictionary synonyms. Two words can be close because they appear in similar sentences, which is why an antonym can outscore a synonym here.

4 Its personality measured
Qwen3 8B
DeepSeek V3
Mistral 7B

This model splits lanolin into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

rare common
concrete abstract
casual formal
everyday technical
negative positive
mild intense
powerless powerful
small big

This model splits lanolin into 3 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

rare common
concrete abstract
casual formal
everyday technical
negative positive
mild intense
powerless powerful
small big

This model splits lanolin into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

rare common
concrete abstract
casual formal
everyday technical
negative positive
mild intense
powerless powerful
small big

Scores are projections onto axes we defined from anchor words, not labels the model assigns.

5 Surprising neighbours measured
Qwen3 8B
DeepSeek V3
Mistral 7B

This model splits lanolin into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to lanolin. That gap is the model’s own learned association.

This model splits lanolin into 3 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to lanolin. That gap is the model’s own learned association.

This model splits lanolin into 2 pieces, so it has no vector of its own here: this is the average of its fragments, and the results below are correspondingly rough.

These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to lanolin. That gap is the model’s own learned association.

These are statistical associations in the training data, not the model thinking.