INDEX
Explanations
mentions of the word "abortion."
New Auto-Interp
Negative Logits
gia
-0.16
tainment
-0.16
ibern
-0.15
ÙĨدÙĩ
-0.15
rank
-0.14
yper
-0.14
agos
-0.14
Powered
-0.14
Kara
-0.14
Rodrig
-0.14
POSITIVE LOGITS
riel
0.18
enko
0.16
ritel
0.16
Casey
0.15
antly
0.15
eward
0.14
ÃŃl
0.14
_FP
0.14
sher
0.14
OLON
0.14
Activations Density 0.022%