INDEX
Explanations
clothing items and accessories
clothing and fashion accessories
New Auto-Interp
Negative Logits
otten
-0.74
Refer
-0.73
enthal
-0.72
Interest
-0.71
nuclear
-0.69
issions
-0.69
KNOWN
-0.68
Dev
-0.68
DEV
-0.67
Site
-0.66
POSITIVE LOGITS
worn
1.30
adorned
1.23
draped
1.10
cloth
1.06
wearer
1.04
fashioned
1.01
clad
1.00
sleeves
1.00
trousers
1.00
jacket
0.99
Activations Density 0.152%