INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.09
1:0.08
2:0.07
3:0.08
4:0.09
5:0.08
6:0.07
7:0.08
8:0.08
9:0.08
10:0.07
11:0.08
Negative Logits
grave
-2.32
ayn
-1.73
atel
-1.69
onel
-1.69
cca
-1.64
vetted
-1.64
nikov
-1.63
hid
-1.61
urance
-1.60
llular
-1.60
POSITIVE LOGITS
ESE
1.89
Chick
1.86
Jong
1.82
bush
1.79
Kro
1.72
Dek
1.71
ween
1.68
mons
1.65
Dutch
1.64
Dutch
1.61
Activations Density 0.000%
No Known Activations
This feature has no known activations.