INDEX
Explanations
mentions of political figures and official positions
names of political leaders and their titles
New Auto-Interp
Negative Logits
rawdownloadcloneembedreportprint
-0.75
interpol
-0.69
CRIP
-0.69
Stud
-0.69
ãĥ¼ãĤ¯
-0.67
rint
-0.66
webs
-0.65
paces
-0.63
Phant
-0.62
manuscript
-0.62
POSITIVE LOGITS
appoint
0.81
anyahu
0.81
appointed
0.78
gov
0.77
Jinping
0.75
appointing
0.75
uty
0.74
vowed
0.73
oÄŁan
0.73
iani
0.72
Activations Density 0.256%