INDEX
Explanations
opening parentheses in various contexts or structures
New Auto-Interp
Negative Logits
*
-0.36
(
-0.36
$
-0.34
_
-0.31
&
-0.29
@
-0.29
[
-0.28
%
-0.24
$\
-0.22
"
-0.22
POSITIVE LOGITS
...)↵
0.23
â̦)
0.22
/*
0.20
__)
0.20
)
0.19
--)
0.19
/**
0.18
a
0.17
,)
0.17
).__
0.17
Activations Density 0.216%