INDEX
Explanations
references to casualties and incidents involving death or injury
New Auto-Interp
Negative Logits
aval
-0.16
599
-0.15
igh
-0.14
Named
-0.14
uspended
-0.14
Vin
-0.14
hood
-0.14
aha
-0.14
appropriate
-0.13
amburg
-0.13
POSITIVE LOGITS
leur
0.20
_RW
0.14
olet
0.14
">//
0.14
upro
0.14
-Origin
0.14
idis
0.13
toa
0.13
dcc
0.13
_DC
0.13
Activations Density 0.098%