INDEX
Explanations
references to the popularity of subjects or entities
New Auto-Interp
Negative Logits
esis
-0.60
etje
-0.58
hypnosis
-0.58
bandages
-0.57
aglio
-0.56
Autoritní
-0.56
endometriosis
-0.55
cervix
-0.55
endometri
-0.54
retum
-0.53
POSITIVE LOGITS
popular
1.91
Popular
1.78
popular
1.78
Popular
1.73
POPULAR
1.70
populares
1.42
populaires
1.37
populaire
1.36
популяр
1.29
popularity
1.28
Activations Density 0.004%