INDEX
Explanations
mentions of the word "rape"
references to the topic of rape
New Auto-Interp
Negative Logits
uchin
-0.89
quickShipAvailable
-0.83
Solitaire
-0.75
ormons
-0.74
ocular
-0.71
dilig
-0.70
OTAL
-0.69
peror
-0.68
BLIC
-0.67
ixir
-0.67
POSITIVE LOGITS
rape
1.19
Rape
1.08
raped
0.94
quez
0.92
borg
0.92
rape
0.91
rapes
0.88
Sexual
0.86
victims
0.84
raping
0.84
Activations Density 0.022%