INDEX
Explanations
references to gender, particularly focusing on men and women
New Auto-Interp
Negative Logits
expandindo
-0.77
skolan
-0.66
EconPapers
-0.63
Photocase
-0.61
']")
-0.59
autorytatywna
-0.57
Scopus
-0.57
['./
-0.56
personnelles
-0.56
المعيارى
-0.55
POSITIVE LOGITS
who
0.83
thol
0.71
men
0.70
Men
0.69
MEN
0.69
hunt
0.67
volent
0.59
agerie
0.58
aced
0.58
folk
0.58
Activations Density 0.085%