INDEX
Explanations
references to women in history and their achievements
New Auto-Interp
Negative Logits
venge
-0.17
輪
-0.15
geb
-0.14
trak
-0.14
_strerror
-0.14
CCA
-0.14
adt
-0.14
ujet
-0.14
_tD
-0.13
ortho
-0.13
POSITIVE LOGITS
atu
0.16
Bram
0.16
(library
0.14
abd
0.14
uristic
0.14
ecta
0.14
jets
0.14
dead
0.14
imler
0.13
Rena
0.13
Activations Density 0.068%