INDEX
Explanations
repeated elements or patterns in the text
Text after "Update" or edit number
dates, names, and specific identifiers
New Auto-Interp
Negative Logits
,
-0.81
.
-0.78
to
-0.60
?
-0.60
of
-0.55
!
-0.55
Barbier
-0.54
;
-0.54
:
-0.53
-0.53
POSITIVE LOGITS
Sarm
0.94
LK
0.88
Efq
0.85
MPR
0.83
PRD
0.82
doubtnut
0.82
bave
0.81
itſelf
0.80
Coss
0.79
Shakspeare
0.78
Activations Density 1.830%