INDEX
Explanations
references to death row and legal proceedings related to inmates
New Auto-Interp
Negative Logits
PROTO
-0.16
COPE
-0.14
LEV
-0.14
Beh
-0.14
kening
-0.14
梨
-0.14
Jury
-0.13
trieve
-0.13
Beh
-0.13
lev
-0.13
POSITIVE LOGITS
DNA
0.25
DNA
0.20
nw
0.17
convictions
0.16
dna
0.15
Innoc
0.15
owitz
0.15
oot
0.15
redo
0.15
conviction
0.14
Activations Density 0.033%