INDEX
Explanations
punctuation marks and sentence endings
New Auto-Interp
Negative Logits
,
-1.86
.
-0.59
mtable
-0.50
OnInit
-0.49
TextAppearance
-0.44
intStringLen
-0.43
aneity
-0.43
‘
-0.42
trange
-0.42
prnewswire
-0.41
POSITIVE LOGITS
️
0.64
'.
0.62
).
0.62
’.
0.62
︎
0.61
${0.60
”,
0.59
_.
0.58
」,
0.58
'))
0.57
Activations Density 0.993%