INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
Goy
1.15
dag
0.87
pl
0.84
Dogg
0.84
psy
0.83
Paige
0.82
indy
0.80
Skyl
0.79
pathologic
0.79
Lank
0.78
POSITIVE LOGITS
FeCl
1.04
Alton
1.04
Brum
0.93
ferr
0.93
Fe
0.92
input
0.89
iron
0.89
Input
0.88
iron
0.88
Input
0.87
Activations Density 2.185%