INDEX
Explanations
math formula environments, particularly the alignment characters within them.
New Auto-Interp
Negative Logits
setVerticalGroup
-0.78
Willoughby
-0.77
Herrick
-0.72
rispar
-0.71
estacks
-0.71
Dubuque
-0.70
Barrington
-0.69
Jacobsen
-0.69
iecie
-0.68
huriyet
-0.68
POSITIVE LOGITS
&\
1.48
&\
1.43
,$_
0.77
Sif
0.75
'>
0.75
RIV
0.73
tetés
0.73
"+
0.72
...</
0.72
="\
0.71
Activations Density 0.005%