INDEX
Explanations
references to cash or monetary transactions
New Auto-Interp
Negative Logits
stal
-0.17
DataSource
-0.16
esti
-0.16
reta
-0.16
astos
-0.16
olon
-0.15
erek
-0.15
zem
-0.15
esting
-0.15
issing
-0.14
POSITIVE LOGITS
mere
0.28
flow
0.17
back
0.16
mina
0.16
erman
0.16
ola
0.16
iola
0.15
iers
0.15
mir
0.15
ew
0.15
Activations Density 0.011%