INDEX
Explanations
references to the superhero character Spider-Man
New Auto-Interp
Negative Logits
brance
-0.89
ufact
-0.75
usable
-0.72
essage
-0.69
enture
-0.67
Limbaugh
-0.65
Miranda
-0.62
uction
-0.62
iband
-0.62
bered
-0.61
POSITIVE LOGITS
Oak
0.95
lings
0.92
monkey
0.92
Spider
0.88
Spider
0.88
web
0.85
hook
0.83
webs
0.82
Bob
0.78
hawk
0.78
Activations Density 0.022%