INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.08
1:0.05
2:0.08
3:0.09
4:0.09
5:0.07
6:0.07
7:0.08
8:0.08
9:0.08
10:0.08
11:0.07
Negative Logits
rio
-1.72
nic
-1.69
Tuc
-1.58
flora
-1.57
ophy
-1.55
monop
-1.48
opsis
-1.47
fa
-1.44
cob
-1.44
Ivan
-1.43
POSITIVE LOGITS
proxy
1.61
iatrics
1.59
shorthand
1.56
ヘ
1.53
thood
1.48
reass
1.47
yssey
1.45
lished
1.45
continue
1.44
arbitration
1.43
Activations Density 0.000%
No Known Activations
This feature has no known activations.