1
Your word
measured
“hot stove”
Definitions come from WordNet, a hand-curated dictionary.
used of physical heat; having a high or higher than desirable temperature or giving off heat or feeling or causing a sensation of heat or burning
暑い is Japanese for hot, 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.
“hot stove”
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 暑い itself, not hot — 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.
cold is the dictionary opposite of hot, yet this model puts it closer than every one of the 3 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 hot. 3 of 5 dictionary synonyms are in this build; the rest have no vector to compare yet.
cold is the dictionary opposite of hot, yet this model puts it closer than every one of the 3 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 hot. 3 of 5 dictionary synonyms are in this build; the rest have no vector to compare yet.
cold is the dictionary opposite of hot, yet this model puts it closer than every one of the 3 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 hot. 3 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.
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 hot. 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 hot. 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 hot. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.