INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
igi
-0.15
ibold
-0.15
aca
-0.14
Ý
-0.14
лем
-0.14
ikal
-0.14
oden
-0.14
ξι
-0.13
lemn
-0.13
uku
-0.13
POSITIVE LOGITS
355
0.15
³³³³³³³³³³³
0.15
oger
0.15
Jewish
0.14
×
0.14
ynet
0.14
.azure
0.14
kli
0.14
363
0.14
×ķ
0.14
Activations Density 0.000%
No Known Activations
This feature has no known activations.