INDEX
Explanations
references to women, reproductive health, and social issues related to abortion
New Auto-Interp
Negative Logits
eres
-0.17
ÎĵεÏī
-0.14
otive
-0.14
SWG
-0.14
oyer
-0.14
Mum
-0.14
orio
-0.14
ount
-0.13
NDEBUG
-0.13
elson
-0.13
POSITIVE LOGITS
Banc
0.17
лоÑĤ
0.16
481
0.15
urret
0.14
Wahl
0.14
affen
0.14
perc
0.14
vyrob
0.14
æľĽ
0.14
mint
0.14
Activations Density 0.252%