1
Your word
measured
“the county has a population of 12,345 people”
Definitions come from WordNet, a hand-curated dictionary.
(United Kingdom) a region created by territorial division for the purpose of local government
condado is Spanish for county, and every measurement below was made on that English word. Definitions come from English WordNet; Open Multilingual WordNet supplies the Spanish headword, not a Spanish definition.
Panels 3, 4 and 5 are computed per model. Switch to see them disagree.
“the county has a population of 12,345 people”
Definitions come from WordNet, a hand-curated dictionary.
This panel splits condado itself, not county — 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 county.
WordNet lists none for this word.
Shade shows how close the model puts each word to county.
WordNet lists none for this word.
Shade shows how close the model puts each word to county.
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 county. 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 county. 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 county. That gap is the model’s own learned association.
These are statistical associations in the training data, not the model thinking.