INDEX
Explanations
references to male individuals or categories of people in a variety of contexts
New Auto-Interp
Negative Logits
gian
-0.57
Audiodateien
-0.55
LookAnd
-0.54
occupe
-0.53
veldig
-0.52
dieu
-0.52
HtmlAttribute
-0.52
Hentet
-0.51
الإنجليزية
-0.50
Réponses
-0.50
POSITIVE LOGITS
nahilalakip
0.54
GraphicsUnit
0.52
Assista
0.52
مُعرِّف
0.52
FormControl
0.51
APORE
0.51
avits
0.50
/-/
0.49
ExtendWith
0.48
immediately
0.48
Activations Density 0.509%