INDEX
Explanations
instances of injuries and casualties in violent events
New Auto-Interp
Negative Logits
Ỽ
-0.14
_ipc
-0.14
resolution
-0.14
equivalents
-0.14
avaÅŁ
-0.14
æī§
-0.14
itz
-0.14
REFERRED
-0.14
ãĤ
-0.14
ownload
-0.14
POSITIVE LOGITS
allis
0.17
pf
0.15
åī²
0.15
div
0.15
ym
0.14
apple
0.14
forb
0.14
illus
0.13
whom
0.13
pb
0.13
Activations Density 0.017%