INDEX
Explanations
references to women and their roles in various contexts
New Auto-Interp
Negative Logits
ames
-0.16
ellar
-0.15
aucoup
-0.15
ëģĶ
-0.15
ologi
-0.14
emd
-0.14
ople
-0.14
gan
-0.14
.gif
-0.14
ental
-0.14
POSITIVE LOGITS
ÑĢеб
0.14
NI
0.14
ucha
0.14
ska
0.14
921
0.14
azaar
0.14
sông
0.13
804
0.13
arden
0.13
Deer
0.13
Activations Density 0.019%