INDEX
Explanations
references to violence and injuries
New Auto-Interp
Negative Logits
fingert
-0.07
ENU
-0.07
fing
-0.07
etooth
-0.07
APT
-0.06
fingertips
-0.06
noses
-0.06
finger
-0.06
paginator
-0.06
.Orientation
-0.06
POSITIVE LOGITS
vital
0.13
Vital
0.10
vit
0.10
jug
0.10
chest
0.09
heart
0.09
unprotected
0.09
vulnerable
0.08
jug
0.08
Chest
0.08
Activations Density 0.028%