INDEX
Explanations
color-related terms or descriptions
references to color in various contexts
New Auto-Interp
Negative Logits
idem
-0.91
olicy
-0.79
inen
-0.78
ILY
-0.75
CVE
-0.75
psons
-0.72
CLA
-0.71
Dur
-0.70
doms
-0.69
rogen
-0.69
POSITIVE LOGITS
colors
1.13
dots
1.12
stripes
1.10
colours
1.10
colored
1.04
striped
1.01
ribbon
0.97
coloured
0.95
tint
0.90
dye
0.90
Activations Density 0.021%