INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
BOX
0.78
Bex
0.73
Bick
0.73
Bos
0.71
box
0.71
Boxes
0.71
Robles
0.70
ABO
0.68
ox
0.68
kotak
0.68
POSITIVE LOGITS
Ferr
1.04
Tar
1.04
UNC
0.99
Ferr
0.98
Tar
0.95
Falconer
0.95
Flynn
0.92
mineral
0.90
itale
0.90
arzy
0.89
Activations Density 2.955%