INDEX
Explanations
numerical values related to time durations and monetary amounts
New Auto-Interp
Negative Logits
sbin
-0.16
EI
-0.15
adb
-0.15
ismu
-0.15
wolf
-0.15
ovnÃŃ
-0.14
/mm
-0.14
еÑĢов
-0.13
åĽ
-0.13
abwe
-0.13
POSITIVE LOGITS
432
0.16
antro
0.16
30
0.14
234
0.14
rens
0.13
Moff
0.13
146
0.13
اتÙĩ
0.13
uppen
0.13
SSA
0.13
Activations Density 0.076%