INDEX
Explanations
references to women's rights and related issues in the context of hijab and dress codes
New Auto-Interp
Negative Logits
rir
-0.16
burgh
-0.16
herits
-0.15
жа
-0.15
Micha
-0.14
emes
-0.14
airo
-0.14
ktop
-0.14
ffa
-0.14
ساÙĨ
-0.14
POSITIVE LOGITS
ahi
0.18
æĮĻ
0.18
ntag
0.16
.ejb
0.15
Conspiracy
0.15
851
0.14
.Parcel
0.14
icina
0.14
ider
0.14
ůj
0.14
Activations Density 0.219%