INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.09
1:0.05
2:0.07
3:0.08
4:0.09
5:0.07
6:0.07
7:0.08
8:0.08
9:0.07
10:0.09
11:0.09
Negative Logits
includes
-1.92
ukong
-1.90
û
-1.75
ufact
-1.70
ultimate
-1.68
Appearance
-1.67
bris
-1.64
origin
-1.59
Images
-1.58
displayText
-1.57
POSITIVE LOGITS
toes
1.79
quake
1.75
yawn
1.67
pse
1.64
paras
1.57
behavi
1.55
neigh
1.53
chorus
1.53
��
1.52
trickle
1.51
Activations Density 0.000%
No Known Activations
This feature has no known activations.