INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.07
1:0.07
2:0.08
3:0.08
4:0.09
5:0.08
6:0.08
7:0.08
8:0.08
9:0.08
10:0.09
11:0.07
Negative Logits
Siber
-1.61
lich
-1.59
Wyr
-1.58
}"
-1.50
Scion
-1.49
Grimm
-1.46
footh
-1.45
Azerb
-1.45
rison
-1.44
…."
-1.42
POSITIVE LOGITS
ensitivity
1.73
clerosis
1.69
FML
1.63
galitarian
1.62
Vote
1.56
udos
1.54
Appeal
1.52
GG
1.49
LO
1.49
omnia
1.48
Activations Density 0.000%
No Known Activations
This feature has no known activations.