INDEX
Explanations
references to films and elements associated with horror and low-budget genres
New Auto-Interp
Negative Logits
ucz
-0.08
(es
-0.07
nan
-0.07
884
-0.07
nét
-0.07
emma
-0.06
/--
-0.06
lfw
-0.06
lek
-0.06
ï¸ı
-0.06
POSITIVE LOGITS
/simple
0.08
-level
0.08
weg
0.08
adoo
0.08
-style
0.07
(low
0.07
-grade
0.07
-type
0.07
arker
0.07
-priced
0.07
Activations Density 0.039%