INDEX
Explanations
descriptions of clothing items being worn
items of clothing being worn by individuals
New Auto-Interp
Negative Logits
ancock
-0.85
emetery
-0.85
llor
-0.81
Dhabi
-0.80
orrow
-0.79
terness
-0.77
enario
-0.76
agonist
-0.74
Distance
-0.74
nown
-0.72
POSITIVE LOGITS
clothes
0.91
sleeves
0.90
camouflage
0.87
masks
0.83
clipboard
0.83
gloves
0.82
shirt
0.81
socks
0.81
jacket
0.81
sweats
0.81
Activations Density 0.141%