INDEX
Explanations
patterns related to clothing items, specifically T-shirts
references to T-shirts
New Auto-Interp
Negative Logits
antid
-0.67
omn
-0.65
richer
-0.60
academ
-0.59
potassium
-0.59
ãģ®éŃĶ
-0.58
quar
-0.58
dense
-0.57
digestion
-0.57
intel
-0.57
POSITIVE LOGITS
shirt
1.41
shirts
1.39
rex
1.08
shaped
0.99
minus
0.96
Rex
0.95
mobile
0.90
1000
0.85
Mobile
0.84
Sh
0.80
Activations Density 0.029%