INDEX
Explanations
various mentions of "themes" and their associated contexts
New Auto-Interp
Negative Logits
Cire
-0.79
AlterField
-0.72
SPS
-0.70
expandindo
-0.69
bisous
-0.69
avoit
-0.68
مصرى
-0.68
rhestr
-0.67
Lookout
-0.67
willow
-0.66
POSITIVE LOGITS
Theme
1.91
theme
1.87
themes
1.85
Theme
1.70
theme
1.70
THEME
1.66
THEME
1.66
Themes
1.63
themes
1.50
Themes
1.49
Activations Density 0.043%