INDEX
Explanations
descriptions or contexts involving male individuals
references to males and their characteristics
New Auto-Interp
Negative Logits
OLOG
-0.77
lich
-0.76
RECT
-0.71
thumbnails
-0.71
Assembly
-0.67
Angle
-0.67
Planet
-0.67
bull
-0.65
Chest
-0.65
Airl
-0.63
POSITIVE LOGITS
cius
0.93
aurus
0.87
paces
0.86
cale
0.85
mith
0.84
folk
0.80
avior
0.79
querade
0.79
ettings
0.79
icides
0.78
Activations Density 0.021%