INDEX
Explanations
references to the color gray or grey in a variety of contexts
references to the color gray or grey
New Auto-Interp
Negative Logits
========
-0.85
̶
-0.81
ugal
-0.80
ÄŁ
-0.78
aptic
-0.76
=-=-=-=-
-0.75
CVE
-0.74
uador
-0.74
odium
-0.74
olkien
-0.73
POSITIVE LOGITS
hound
1.22
beard
0.93
shading
0.88
ish
0.86
hawk
0.84
berry
0.83
Metallic
0.80
Goose
0.80
wolf
0.78
tint
0.77
Activations Density 0.017%