INDEX
Explanations
terms related to women's rights and health issues
New Auto-Interp
Negative Logits
بد
-0.15
illo
-0.14
ogl
-0.14
zent
-0.14
ilim
-0.14
еÑĢÑĮ
-0.13
rtl
-0.13
agnost
-0.13
mpp
-0.13
hes
-0.13
POSITIVE LOGITS
elijk
0.16
urity
0.15
china
0.15
iode
0.15
occo
0.15
:UITableView
0.14
AE
0.14
inois
0.14
vie
0.14
inel
0.13
Activations Density 0.102%