INDEX
Explanations
words related to men's clothing and fashion
references to clothing and wearable items
New Auto-Interp
Negative Logits
Colon
-0.74
anon
-0.69
bil
-0.66
Franklin
-0.64
udic
-0.62
CTR
-0.61
scal
-0.60
edy
-0.59
opol
-0.59
ham
-0.59
POSITIVE LOGITS
wear
4.61
Wear
2.20
apparel
1.65
wearable
1.63
wear
1.63
footwear
1.40
garments
1.39
worn
1.38
Clothing
1.31
attire
1.28
Activations Density 0.021%