INDEX
Explanations
descriptions of physical characteristics, particularly related to the color brown
instances of the word "brown."
New Auto-Interp
Negative Logits
SPONSORED
-0.78
oteric
-0.75
REL
-0.73
Ces
-0.72
NRS
-0.72
ITAL
-0.71
Xi
-0.70
DCS
-0.70
OF
-0.70
Hung
-0.68
POSITIVE LOGITS
ish
1.01
brown
0.98
coat
0.93
berry
0.86
cake
0.85
coats
0.85
bread
0.83
beard
0.83
colored
0.83
pudding
0.82
Activations Density 0.008%