INDEX
Explanations
words related to body parts, particularly the waist and shoulders
terms related to body measurements and physical structure
New Auto-Interp
Negative Logits
itsch
-0.86
ative
-0.82
ativity
-0.79
ophy
-0.77
atives
-0.75
UE
-0.72
Mehran
-0.70
opsis
-0.67
ongyang
-0.66
atory
-0.64
POSITIVE LOGITS
coat
1.06
circumference
0.86
band
0.85
belt
0.76
dress
0.75
pless
0.75
fed
0.74
vel
0.74
waist
0.73
mast
0.73
Activations Density 0.037%