INDEX
Explanations
references to death row and capital punishment cases
New Auto-Interp
Negative Logits
validationResult
-0.16
andal
-0.16
512
-0.14
ibri
-0.14
sobie
-0.14
harassing
-0.14
å¨ĺ
-0.14
760
-0.14
888
-0.13
subpoena
-0.13
POSITIVE LOGITS
execution
0.28
Execution
0.24
executions
0.24
death
0.23
execution
0.22
Execution
0.21
Death
0.21
death
0.21
hang
0.20
Death
0.19
Activations Density 0.028%