INDEX
Explanations
pain-related numerical expressions and currency symbols
New Auto-Interp
Negative Logits
^(@)
-1.12
ſelves
-1.06
bezeichneter
-1.03
ſelf
-1.02
ViewFeatures
-1.00
iſt
-1.00
)");
-0.99
/>";
-0.96
{}));-0.95
$.
-0.95
POSITIVE LOGITS
$
0.87
$\
0.78
1
0.69
,
0.69
($
0.66
<i>
0.63
4
0.60
2
0.60
<em>
0.60
0.60
Activations Density 0.113%