INDEX
Explanations
references to the fictional character Spider-Man
New Auto-Interp
Negative Logits
brance
-0.81
subsidized
-0.67
igated
-0.65
bered
-0.64
essage
-0.64
iband
-0.63
ufact
-0.63
usable
-0.63
icative
-0.63
forc
-0.61
POSITIVE LOGITS
web
1.00
Oak
0.98
monkey
0.96
lings
0.96
Spider
0.92
Spider
0.92
hook
0.85
webs
0.83
walker
0.82
ling
0.79
Activations Density 0.039%