INDEX
Explanations
references to females, specifically girls, in various contexts
New Auto-Interp
Negative Logits
ModelExpression
-0.71
__":
-0.60
reportWebVitals
-0.56
ctor
-0.56
Brutus
-0.56
Madura
-0.54
arşivlendi
-0.54
milch
-0.53
mouseleave
-0.52
mapreduce
-0.51
POSITIVE LOGITS
IContainer
0.97
Girl
0.74
girl
0.74
Girl
0.73
Италијани
0.70
girl
0.68
GIRL
0.66
extAlignment
0.66
ьаж
0.64
LayoutStyle
0.62
Activations Density 0.104%