INDEX
Explanations
words related to clothing items
the occurrences of the word "lee."
New Auto-Interp
Negative Logits
Seym
-0.80
nai
-0.71
ico
-0.70
CPC
-0.70
onut
-0.69
orate
-0.68
achu
-0.67
rices
-0.66
framework
-0.64
icated
-0.64
POSITIVE LOGITS
pless
1.05
lee
0.87
ves
0.86
vel
0.86
vec
0.82
ving
0.82
ce
0.82
heed
0.82
scill
0.81
UGH
0.81
Activations Density 0.011%