INDEX
Explanations
references to global events or initiatives related to women's rights and education
New Auto-Interp
Negative Logits
abil
-0.17
orgh
-0.16
öl
-0.16
éĽ¢
-0.14
antz
-0.14
acam
-0.14
kv
-0.14
906
-0.14
strand
-0.13
enda
-0.13
POSITIVE LOGITS
Hosp
0.17
ššÃŃ
0.15
uye
0.15
ocrats
0.15
ormsg
0.14
umph
0.14
-Smith
0.14
ipeg
0.14
oter
0.13
defgroup
0.13
Activations Density 0.037%