INDEX
Explanations
significant linguistic patterns or features in different scripts and phonetics
Non-English text or symbols
non-English characters and archaic words
New Auto-Interp
Negative Logits
-1.04
,
-0.95
in
-0.89
-
-0.83
(
-0.82
"
-0.80
-
-0.80
to
-0.79
for
-0.79
of
-0.78
POSITIVE LOGITS
Efq
1.82
myſelf
1.73
ſind
1.72
་་
1.65
―――――
1.63
Anſ
1.60
iſt
1.59
photolibrary
1.57
itſelf
1.56
Houſe
1.55
Activations Density 0.016%