INDEX
Explanations
words related to articles of clothing, specifically coats
references to various types of coats
New Auto-Interp
Negative Logits
raltar
-0.71
NOR
-0.71
gren
-0.62
reme
-0.62
affiliated
-0.61
foreseen
-0.61
cca
-0.61
Zar
-0.61
friend
-0.61
resource
-0.60
POSITIVE LOGITS
coats
1.17
coat
1.17
Coat
0.96
pins
0.85
coating
0.84
coated
0.77
grain
0.77
creen
0.77
coat
0.76
jacket
0.74
Activations Density 0.010%