INDEX
Explanations
references to items or experiences involving female characters or themes
New Auto-Interp
Negative Logits
aille
-0.16
iest
-0.15
Qualität
-0.15
acular
-0.15
gor
-0.15
afx
-0.14
vod
-0.14
}elseif
-0.14
buie
-0.14
jah
-0.14
POSITIVE LOGITS
tow
0.20
uft
0.17
sterol
0.15
ombo
0.15
ères
0.15
handy
0.14
celik
0.14
ÙĬÙĪÙĨ
0.14
SSION
0.14
Ñħол
0.14
Activations Density 0.189%