INDEX
Explanations
mentions of the name "Ernest."
New Auto-Interp
Negative Logits
ãģ¾ãģŁ
-0.15
atori
-0.15
aterno
-0.15
elay
-0.15
osit
-0.14
ishes
-0.14
noop
-0.14
->{'-0.14
μοί
-0.14
ÑģÑĤвоÑĢ
-0.14
POSITIVE LOGITS
ine
0.24
o
0.20
Hem
0.19
berger
0.19
INE
0.19
ynn
0.18
hem
0.17
ÙĩÙħÛĮÙĨ
0.16
hausen
0.16
ina
0.16
Activations Density 0.006%