INDEX
Explanations
the prefix "pri" in various languages
New Auto-Interp
Negative Logits
a
-1.20
the
-1.17
,
-1.16
an
-1.12
-1.03
in
-1.00
I
-0.94
so
-0.93
(
-0.91
K
-0.89
POSITIVE LOGITS
Monfieur
2.64
Efq
2.55
myſelf
2.52
itſelf
2.47
Houſe
2.47
Jefus
2.47
Theſe
2.45
Reſ
2.44
houſe
2.42
pleaſure
2.42
Activations Density 3.262%