1
Your word
measured
Definitions come from WordNet, a hand-curated dictionary.
a laborer who loads and unloads vessels in a port
中仕 is Japanese for loader, 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 中仕 itself, not loader — 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 loader. 0 of 8 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to loader. 0 of 8 dictionary synonyms are in this build; the rest have no vector to compare yet.
Shade shows how close the model puts each word to loader. 0 of 8 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 loader. 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 loader. 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 loader. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.