INDEX
Explanations
time-related information, particularly in the context of sports events
New Auto-Interp
Negative Logits
landa
-0.17
stadt
-0.15
malink
-0.15
acos
-0.15
lob
-0.15
ake
-0.14
mdir
-0.14
arta
-0.14
禮
-0.14
æij
-0.14
POSITIVE LOGITS
bases
0.16
oron
0.15
ecut
0.14
ertz
0.14
isine
0.14
Wahl
0.14
anging
0.14
Taj
0.14
jk
0.13
uali
0.13
Activations Density 0.013%