INDEX
Explanations
terms related to feminism and feminist movements
New Auto-Interp
Negative Logits
manship
-0.18
istrovstvÃŃ
-0.17
suz
-0.15
anke
-0.15
ed
-0.15
Ñģк
-0.14
iations
-0.14
ites
-0.14
edo
-0.14
hal
-0.14
POSITIVE LOGITS
ichel
0.15
rub
0.15
ylland
0.15
-len
0.15
pson
0.15
-leaning
0.15
/legal
0.14
ilon
0.13
republic
0.13
(SP
0.13
Activations Density 0.096%