canine

noun 4 senses

one of the four pointed conical teeth (two in each jaw) located between the incisors and the premolars

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 4 senses 7 synonyms

Definitions come from WordNet, a hand-curated dictionary.

2 To an AI, it's pieces measured
DeepSeek V3 canine 1 token
Mistral 7B can ine 2 tokens
Qwen3 8B canine 1 token

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

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

Dictionary synonyms measured

cuspid0.11 dogtooth0.05 canine tooth eyetooth eye tooth canid laniary

Shade shows how close the model puts each word to canine. 2 of 7 dictionary synonyms are in this build; the rest have no vector to compare yet.

Dictionary synonyms measured

dogtooth0.13 cuspid0.02 canine tooth eyetooth eye tooth canid laniary

Shade shows how close the model puts each word to canine. 2 of 7 dictionary synonyms are in this build; the rest have no vector to compare yet.

This model splits canine 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.

Dictionary synonyms measured

cuspid0.12 dogtooth0.12 canine tooth eyetooth eye tooth canid laniary

Shade shows how close the model puts each word to canine. 2 of 7 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
rare common
concrete abstract
casual formal
everyday technical
negative positive
mild intense
powerless powerful
small big
rare common
concrete abstract
casual formal
everyday technical
negative positive
mild intense
powerless powerful
small big

This model splits canine 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

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

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

This model splits canine 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 canine. That gap is the model’s own learned association.

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