INDEX
Explanations
mentions of clothing items
references to clothing
New Auto-Interp
Negative Logits
odcast
-0.71
ntil
-0.68
utherford
-0.68
umar
-0.66
ctive
-0.65
Woodward
-0.65
unanim
-0.64
ĵĺ
-0.63
£ı
-0.63
ĺħ
-0.62
POSITIVE LOGITS
pins
1.07
worn
0.99
clothes
0.99
clothing
0.94
puter
0.94
leeve
0.94
bags
0.91
bag
0.90
garments
0.89
apparel
0.88
Activations Density 0.014%