INDEX
Explanations
elements of storytelling and narrative structure in film
New Auto-Interp
Negative Logits
erif
-0.16
Eh
-0.15
Samar
-0.14
itag
-0.14
uluk
-0.14
errick
-0.14
ohl
-0.14
Horton
-0.14
htag
-0.14
zman
-0.14
POSITIVE LOGITS
zier
0.19
Figure
0.17
atmos
0.16
figura
0.16
Aires
0.16
Char
0.15
associ
0.15
ÃŃk
0.15
hell
0.15
dynam
0.15
Activations Density 0.027%