INDEX
Explanations
references to women in positions of leadership or authority
New Auto-Interp
Negative Logits
498
-0.17
ndern
-0.15
PropertyChanged
-0.15
anou
-0.14
crest
-0.14
лÑİÑĩ
-0.13
tah
-0.13
utter
-0.13
δή
-0.13
ponsible
-0.13
POSITIVE LOGITS
Cloth
0.15
elig
0.15
Hindered
0.14
ijken
0.14
]âĢı
0.14
lot
0.14
pane
0.14
Du
0.14
lun
0.13
moi
0.13
Activations Density 0.492%