INDEX
Explanations
references to clothing items, specifically coats
references to coats and outerwear
New Auto-Interp
Negative Logits
Ambro
-0.68
izoph
-0.67
die
-0.65
RELE
-0.65
NOR
-0.65
KNOWN
-0.64
Kut
-0.63
nir
-0.63
ANS
-0.61
ITCH
-0.61
POSITIVE LOGITS
coat
1.00
coats
0.98
pins
0.94
Coat
0.88
manship
0.81
folios
0.80
creen
0.77
coating
0.76
color
0.74
apons
0.73
Activations Density 0.011%