INDEX
Explanations
mentions of the name "Bern."
New Auto-Interp
Negative Logits
ENTRY
-0.16
1
-0.15
gap
-0.15
.YesNo
-0.15
4
-0.15
pec
-0.15
ashi
-0.15
aid
-0.14
cred
-0.14
3
-0.14
POSITIVE LOGITS
sı
0.17
bilt
0.17
avigator
0.17
igel
0.16
exion
0.16
á»iji
0.15
ician
0.15
ldr
0.15
aul
0.14
malar
0.14
Activations Density 0.002%