INDEX
Explanations
the word "himself" and sometimes other words and terms that could be linked with self-reference or possibly self-harm.
New Auto-Interp
Negative Logits
MonoBehaviour
-0.84
owulf
-0.76
Życiorys
-0.72
yship
-0.71
ihnachten
-0.68
ESG
-0.68
rmtree
-0.68
HMI
-0.67
orghini
-0.66
Xna
-0.66
POSITIVE LOGITS
ekš
0.68
"..\..\
0.65
نداره
0.62
vectorielles
0.56
vectorielle
0.56
abstrait
0.55
revanche
0.55
following
0.55
perus
0.54
cluye
0.54
Activations Density 2.067%