INDEX
Explanations
references to financial burdens and obligations related to taxpayers and government expenditures
New Auto-Interp
Negative Logits
icket
-0.15
unpaid
-0.14
@$_
-0.14
----</
-0.14
ê·ł
-0.14
cket
-0.14
abric
-0.14
åĿĬ
-0.14
488
-0.13
Petite
-0.13
POSITIVE LOGITS
fork
0.43
Fork
0.37
forks
0.36
fork
0.35
contribute
0.34
pony
0.34
pon
0.32
contributing
0.32
contributed
0.32
shell
0.31
Activations Density 0.179%