INDEX
Explanations
instances of violent crime and related legal proceedings
New Auto-Interp
Negative Logits
anou
-0.14
layer
-0.14
Cursor
-0.14
mens
-0.14
Inject
-0.14
erf
-0.13
ÙĨد
-0.13
.BLL
-0.13
inject
-0.13
ajo
-0.13
POSITIVE LOGITS
according
0.28
records
0.25
authorities
0.24
according
0.22
According
0.21
According
0.21
preliminary
0.20
reports
0.19
ccording
0.19
sources
0.19
Activations Density 0.152%