INDEX
Explanations
references to pop culture icons and their associated works
New Auto-Interp
Negative Logits
365
-0.15
305
-0.15
éª
-0.14
textInput
-0.14
sumer
-0.13
esty
-0.13
666
-0.13
110
-0.13
antage
-0.13
444
-0.13
POSITIVE LOGITS
characters
0.23
character
0.23
Characters
0.20
fictional
0.20
characters
0.19
Character
0.18
character
0.18
fict
0.18
iconic
0.17
Characters
0.17
Activations Density 0.156%