1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
go back and forth; swing back and forth between two states or conditions
振れる is Japanese for alternating, 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: Qwen3 8B splits this word below the character, so no single token it sees is readable.
This panel splits 振れる itself, not alternating — 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.
direct is the dictionary opposite of alternating, yet this model puts it closer than 3 of the 6 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to alternating, 1 of 8 also appear in the dictionary. 6 of 9 dictionary synonyms are in this build; the rest have no vector to compare yet.
direct is the dictionary opposite of alternating, yet this model puts it closer than 3 of the 6 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to alternating, 1 of 8 also appear in the dictionary. 6 of 9 dictionary synonyms are in this build; the rest have no vector to compare yet.
This model splits alternating 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.
direct is the dictionary opposite of alternating, yet this model puts it closer than 4 of the 6 synonyms it can score. Opposites share the sentences a word lives in, so cosine alone cannot tell them apart - which is why the dictionary seeds this list rather than the geometry.
Shade shows how close the model puts each word to alternating. 6 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.
This model splits alternating 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 alternating. 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 alternating. That gap is the model’s own learned association.
This model splits alternating 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 alternating. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.