INDEX
Explanations
references to specific events or competitions in sports
New Auto-Interp
Negative Logits
abit
-0.16
977
-0.15
067
-0.14
inte
-0.14
bakan
-0.13
_FACT
-0.13
976
-0.13
веÑĤ
-0.13
312
-0.13
çĶŁ
-0.13
POSITIVE LOGITS
omat
0.16
agem
0.15
anca
0.14
hir
0.14
adge
0.14
Execution
0.14
EQ
0.14
redo
0.14
IVEN
0.13
idebar
0.13
Activations Density 0.203%