INDEX
Explanations
references to the Spider-Man franchise
New Auto-Interp
Negative Logits
.fhir
-0.16
SystemService
-0.15
hlas
-0.14
.ManyToMany
-0.14
McCart
-0.14
θη
-0.13
_strcmp
-0.13
lying
-0.13
_POL
-0.13
fty
-0.13
POSITIVE LOGITS
-Man
0.27
man
0.21
web
0.21
-man
0.20
web
0.20
bites
0.19
WEB
0.18
-web
0.18
webs
0.18
webs
0.18
Activations Density 0.004%