INDEX
Explanations
references to criminal activities and related legal proceedings
New Auto-Interp
Negative Logits
assass
-0.17
assassination
-0.17
hostage
-0.15
sue
-0.15
killings
-0.15
éo
-0.15
Killing
-0.14
ogh
-0.14
Χα
-0.14
assassin
-0.14
POSITIVE LOGITS
ascus
0.17
aliases
0.17
convictions
0.17
alias
0.16
charged
0.16
emanc
0.15
conviction
0.15
anship
0.15
conv
0.15
Gam
0.14
Activations Density 0.072%