INDEX
Explanations
references to character development and audience engagement in films
New Auto-Interp
Negative Logits
aja
-0.16
Ministers
-0.16
trom
-0.15
Hayward
-0.15
dsl
-0.15
vpn
-0.15
phem
-0.14
765
-0.14
Cly
-0.14
Boundary
-0.14
POSITIVE LOGITS
Gotham
0.36
Batman
0.35
Bat
0.35
Batman
0.32
Bat
0.32
bat
0.32
BAT
0.30
BAT
0.30
bat
0.27
Ark
0.27
Activations Density 0.044%