INDEX
Explanations
closing parentheses and commas
New Auto-Interp
Negative Logits
[
1.68
((
1.60
(
1.55
(!
1.26
[&
1.17
(!(
1.16
&
1.13
"\
1.12
(^^
1.12
[["
1.11
POSITIVE LOGITS
,)
1.98
..)
1.84
),
1.81
)
1.73
.),
1.66
).
1.65
.)
1.61
~)
1.55
);
1.55
,),
1.54
Activations Density 0.256%