INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.08
3:0.08
4:0.09
5:0.08
6:0.07
7:0.09
8:0.08
9:0.08
10:0.08
11:0.07
Negative Logits
pees
-1.89
quist
-1.83
surfing
-1.77
agna
-1.76
idge
-1.73
quo
-1.70
iscal
-1.70
osher
-1.67
kay
-1.64
steen
-1.63
POSITIVE LOGITS
Imaging
1.59
Directorate
1.55
Haas
1.54
Abstract
1.53
Um
1.52
Analy
1.52
Weak
1.50
Ik
1.50
YN
1.49
Pix
1.48
Activations Density 0.000%
No Known Activations
This feature has no known activations.