INDEX
Explanations
references to "Iron Man"
New Auto-Interp
Negative Logits
enance
-0.88
itia
-0.77
igators
-0.71
arre
-0.70
ired
-0.69
uated
-0.67
idal
-0.65
merce
-0.65
ulhu
-0.64
ĸļ
-0.64
POSITIVE LOGITS
clad
1.14
Python
1.00
Maiden
0.98
Fist
0.94
Age
0.93
works
0.89
heart
0.88
forge
0.88
wood
0.86
claw
0.82
Activations Density 0.005%