INDEX
Explanations
references to color and color-related concepts
New Auto-Interp
Negative Logits
_colors
-0.27
Colors
-0.27
Color
-0.24
colours
-0.23
Colors
-0.23
colourful
-0.22
_colour
-0.21
colors
-0.21
Colour
-0.21
_color
-0.21
POSITIVE LOGITS
scheme
0.33
-coded
0.32
blind
0.32
schemes
0.32
fully
0.31
ation
0.31
Scheme
0.30
chemes
0.27
atura
0.27
cheme
0.27
Activations Density 0.054%