1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
quality of being moderate and avoiding extremes
中庸 is Japanese for moderation, 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.
Definitions come from WordNet, a hand-curated dictionary.
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 中庸 itself, not moderation — 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 moderation. 2 of 5 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to moderation. 2 of 5 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits moderation 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 moderation. 2 of 5 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.
This model splits moderation 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.
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 moderation. 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 moderation. That gap is the model’s own learned association.
This model splits moderation 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 moderation. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.