INDEX
Explanations
mentions of men and women
references to men and women in various contexts related to work and military service
New Auto-Interp
Negative Logits
IVERS
-0.75
ENC
-0.75
VICE
-0.73
Berry
-0.70
DATA
-0.70
Pwr
-0.66
KEN
-0.66
Maximum
-0.65
Customer
-0.64
Side
-0.64
POSITIVE LOGITS
volent
1.25
opausal
1.11
aces
1.07
orah
1.07
aced
1.03
uscript
0.99
endez
0.99
ager
0.97
agers
0.90
folk
0.86
Activations Density 0.071%