INDEX
Explanations
specific names and terms related to politics and finance
mentions of a specific political figure
New Auto-Interp
Negative Logits
heast
-0.84
rations
-0.76
omial
-0.75
ATIONAL
-0.72
heon
-0.70
onial
-0.70
ingham
-0.69
rals
-0.69
ifies
-0.69
itives
-0.69
POSITIVE LOGITS
jriwal
1.18
lers
0.85
chnology
0.73
ught
0.71
irst
0.70
Ke
0.66
eters
0.66
Desk
0.64
worldly
0.64
hunt
0.63
Activations Density 0.018%