INDEX
Explanations
questions and references to uncertainty or confusion
Japanese text followed by punctuation
japanese, chinese, and english phrases
New Auto-Interp
Negative Logits
,
-0.82
a
-0.80
here
-0.73
and
-0.73
est
-0.72
in
-0.72
as
-0.69
on
-0.67
de
-0.67
is
-0.67
POSITIVE LOGITS
ainfi
0.98
auffi
0.97
itſelf
0.93
plufieurs
0.93
GraphicsUnit
0.91
myſelf
0.91
Anſ
0.89
―――――
0.89
PTS
0.89
crdi
0.88
Activations Density 0.004%