INDEX
Explanations
references to body parts related to physical interaction or movement, such as feet, elbows, and hands
New Auto-Interp
Negative Logits
panic
-0.79
ulp
-0.73
Midlands
-0.67
URES
-0.64
grid
-0.64
ulsive
-0.64
scramble
-0.64
ministic
-0.64
cair
-0.63
atari
-0.63
POSITIVE LOGITS
%%%%
0.85
toe
0.78
toe
0.76
bley
0.72
FTWARE
0.71
ardless
0.70
arious
0.69
bernatorial
0.69
oin
0.68
bp
0.68
Activations Density 0.414%