INDEX
Explanations
references to military actions and geopolitical events
New Auto-Interp
Negative Logits
ORM
-0.17
obao
-0.16
HR
-0.15
ICO
-0.14
abies
-0.14
oba
-0.14
é²ģ
-0.14
orm
-0.14
erken
-0.14
ì¼ĵ
-0.14
POSITIVE LOGITS
Sharon
0.26
Sad
0.21
Jordan
0.20
Eh
0.20
IDF
0.20
fed
0.20
Sad
0.20
Begin
0.20
Camp
0.20
Egyptian
0.20
Activations Density 0.033%