INDEX
Explanations
keywords related to women's issues and activism
New Auto-Interp
Negative Logits
prak
-0.16
ضÙĬ
-0.15
ÑŁ
-0.15
ä¿Ĭ
-0.14
WithType
-0.14
Ìī
-0.14
his
-0.14
ibox
-0.13
Dirty
-0.13
athers
-0.13
POSITIVE LOGITS
Women
0.26
women
0.25
Woman
0.23
Women
0.23
woman
0.22
Female
0.21
Womens
0.20
female
0.19
womens
0.18
females
0.18
Activations Density 0.169%