INDEX
Explanations
references to filmmaking or narrative structure
New Auto-Interp
Negative Logits
aron
-0.16
incerely
-0.15
obic
-0.14
ëĿ¼
-0.14
everywhere
-0.14
anchor
-0.14
xde
-0.14
first
-0.14
aller
-0.14
anchor
-0.14
POSITIVE LOGITS
another
0.27
another
0.26
Another
0.23
Another
0.23
-than
0.22
besides
0.21
than
0.21
Than
0.20
THAN
0.19
_than
0.19
Activations Density 0.087%