INDEX
Explanations
terms related to body parts, especially arms
references to "arm" in various contexts
New Auto-Interp
Negative Logits
Sound
-0.77
Vide
-0.77
ween
-0.73
Dough
-0.72
BUR
-0.70
Atmosp
-0.67
due
-0.65
lish
-0.65
Stories
-0.65
VEN
-0.64
POSITIVE LOGITS
aments
1.39
ament
1.38
chair
1.33
ageddon
1.30
illary
1.04
chairs
1.02
amental
0.98
strap
0.96
arm
0.94
ength
0.91
Activations Density 0.015%