INDEX
Explanations
references to baseball players, games, and their performances
New Auto-Interp
Negative Logits
à¤Łà¤ķ
-0.15
rack
-0.14
IRM
-0.14
vre
-0.14
cross
-0.14
ramer
-0.13
MBER
-0.13
ÙĨد
-0.13
oul
-0.13
ingers
-0.13
POSITIVE LOGITS
alte
0.15
ugin
0.15
åª
0.15
éħ
0.15
Mic
0.15
atatype
0.14
zym
0.14
wich
0.14
اÙĦÙħص
0.14
essor
0.14
Activations Density 0.064%