1
Your word
measured
“the British ships dropped anchor and waited for orders from London”
Definitions come from WordNet, a hand-curated dictionary.
(often plural) a command given by a superior (e.g., a military or law enforcement officer) that must be obeyed
命令 is Japanese for order, 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.
“the British ships dropped anchor and waited for orders from London”
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 命令 itself, not order — 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.
disorder is the dictionary opposite of order, yet this model puts it closer than 16 of the 21 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 order, 1 of 8 also appear in the dictionary. 21 of 40 dictionary synonyms are in this build; the rest have no vector to compare yet.
disorder is the dictionary opposite of order, yet this model puts it closer than 14 of the 21 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 order, 1 of 8 also appear in the dictionary. 21 of 40 dictionary synonyms are in this build; the rest have no vector to compare yet.
disorder is the dictionary opposite of order, yet this model puts it closer than 20 of the 21 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 order, 1 of 8 also appear in the dictionary. 21 of 40 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 order. 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 order. 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 order. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.