INDEX
Explanations
references to cash or monetary transactions
New Auto-Interp
Negative Logits
eker
-0.16
olon
-0.15
·»
-0.15
_INFINITY
-0.15
astos
-0.15
egree
-0.15
helm
-0.14
wart
-0.14
herit
-0.14
áct
-0.14
POSITIVE LOGITS
mere
0.35
ew
0.24
ews
0.23
iers
0.22
flow
0.21
ola
0.19
OLA
0.18
flow
0.18
merce
0.18
-flow
0.17
Activations Density 0.012%