1
Your word
measured
“it was not a good idea”
Definitions come from WordNet, a hand-curated dictionary.
the content of cognition; the main thing you are thinking about
idée is French for thought, 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.
“it was not a good idea”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits idée itself, not thought — 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.
forget is the dictionary opposite of thought, yet this model puts it closer than 8 of the 18 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 thought, 2 of 8 also appear in the dictionary. 18 of 29 dictionary synonyms are in this build; the rest have no vector to compare yet.
forget is the dictionary opposite of thought, yet this model puts it closer than 6 of the 18 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 thought, 2 of 8 also appear in the dictionary. 18 of 29 dictionary synonyms are in this build; the rest have no vector to compare yet.
forget is the dictionary opposite of thought, yet this model puts it closer than 4 of the 18 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 thought, 2 of 8 also appear in the dictionary. 18 of 29 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 thought. 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 thought. 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 thought. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.