1
Your word
measured
“he has a cold in the nose”
Definitions come from WordNet, a hand-curated dictionary.
the organ of smell and entrance to the respiratory tract; the prominent part of the face of man or other mammals
鼻 is Japanese for nose, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Japanese headword, not a Japanese definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“he has a cold in the nose”
Definitions come from WordNet, a hand-curated dictionary.
3 of those are a raw byte rather than a character: Qwen3 8B splits this word below the character, so no single token it sees is readable.
3 of those are a raw byte rather than a character: Mistral 7B splits this word below the character, so no single token it sees is readable.
This panel splits 鼻 itself, not nose — a tokenizer does not care what language it is fed. It is the only panel here that does.
This is the tokenizer splitting text, not the model understanding it.
Shade shows how close the model puts each word to nose. 4 of 9 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to nose. 4 of 9 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to nose. 4 of 9 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.
Scores are projections onto axes we defined from anchor words, not labels the model assigns.
These sit just outside the closest neighbours in panel 3, and no dictionary lists any of them as related to nose. 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 nose. 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 nose. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.