INDEX
Explanations
attributes or characteristics of various entities, such as movies, cultures, and people
common themes and motifs related to film and theatrical performances
New Auto-Interp
Negative Logits
oldown
-0.77
cially
-0.75
Secondly
-0.73
Rated
-0.73
proble
-0.72
ccess
-0.71
etimes
-0.70
eworks
-0.70
iversal
-0.70
isl
-0.69
POSITIVE LOGITS
sleek
1.07
lush
0.93
bland
0.92
blond
0.91
colorful
0.89
unrem
0.86
bloated
0.85
flashy
0.83
slick
0.83
cheerful
0.83
Activations Density 0.588%