INDEX
Explanations
instances of the word 'coat'
references to coats and outerwear
New Auto-Interp
Negative Logits
Ambro
-0.75
NOR
-0.70
raltar
-0.70
reme
-0.65
nir
-0.64
resource
-0.64
KNOWN
-0.63
cca
-0.63
accompanied
-0.63
Bunker
-0.62
POSITIVE LOGITS
coat
1.17
coats
1.16
Coat
1.06
pins
0.86
coating
0.84
coated
0.79
coat
0.78
grain
0.77
jacket
0.77
creen
0.76
Activations Density 0.009%