“a diet high in protein”
Definitions come from WordNet, a hand-curated dictionary.
any of a large group of nitrogenous organic compounds that are essential constituents of living cells; consist of polymers of amino acids; essential in the diet of animals for growth and for repair of tissues; can be obtained from meat and eggs and milk and legumes
protide is French for protein, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the French headword, not a French definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“a diet high in protein”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits protide itself, not protein — 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 protein.
WordNet lists none for this word.
Shade shows how close the model puts each word to protein.
WordNet lists none for this word.
Shade shows how close the model puts each word to protein.
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 protein. 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 protein. 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 protein. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.