1
Your word
measured
“young children should not be allowed to stay up until midnight”
Definitions come from WordNet, a hand-curated dictionary.
12 o'clock at night; the middle of the night
ま夜中 is Japanese for midnight, 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.
“young children should not be allowed to stay up until midnight”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits ま夜中 itself, not midnight — 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.
WordNet lists none for this word.
Shade shows how close the model puts each word to midnight.
WordNet lists none for this word.
Shade shows how close the model puts each word to midnight.
WordNet lists none for this word.
Shade shows how close the model puts each word to midnight.
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 midnight. 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 midnight. 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 midnight. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.