INDEX
Explanations
references to women and women's rights issues
New Auto-Interp
Negative Logits
ën
-0.18
INCIDENT
-0.16
urances
-0.15
οÏį
-0.15
females
-0.15
æģ¯
-0.15
eson
-0.14
beck
-0.14
ÃŃcio
-0.14
bject
-0.14
POSITIVE LOGITS
rights
0.27
empowerment
0.23
rights
0.23
suff
0.23
issues
0.22
-rights
0.21
_rights
0.20
Rights
0.20
health
0.20
Issues
0.20
Activations Density 0.026%