INDEX
Explanations
references to programming or technical constructs
New Auto-Interp
Negative Logits
I
-0.71
-0.68
you
-0.64
данный
-0.64
your
-0.63
'
-0.63
‘
-0.63
the
-0.62
i
-0.62
is
-0.61
POSITIVE LOGITS
auffi
1.30
―――――
1.24
uſed
1.20
itſelf
1.17
eſſ
1.14
quæ
1.14
iſt
1.14
ſind
1.13
ſever
1.11
་་
1.11
Activations Density 0.684%