INDEX
Explanations
references to legal and political issues
New Auto-Interp
Negative Logits
еÑĢе
-0.15
Zombies
-0.15
835
-0.14
èĻİ
-0.14
milano
-0.13
Prosper
-0.13
izzo
-0.13
T
-0.13
626
-0.13
oren
-0.13
POSITIVE LOGITS
Julian
0.39
Wiki
0.36
Assange
0.36
Wik
0.35
WikiLeaks
0.35
Manning
0.31
leaks
0.31
Wik
0.31
.wik
0.29
Jul
0.28
Activations Density 0.038%