INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
Kam
0.96
Chu
0.92
Hanna
0.91
Alp
0.90
Kam
0.90
holm
0.89
Cham
0.88
MOR
0.87
Albion
0.86
ALP
0.85
POSITIVE LOGITS
Peters
0.99
Peters
0.99
Kees
0.88
Koz
0.78
Kelly
0.74
Petty
0.74
Seitz
0.74
Kia
0.71
Walters
0.68
koz
0.68
Activations Density 2.465%