INDEX
Explanations
mentions of the concept of democracy
references to democracy
New Auto-Interp
Negative Logits
senal
-0.81
hews
-0.73
notes
-0.72
FU
-0.71
ergy
-0.68
hiba
-0.68
ventory
-0.68
iple
-0.68
Contact
-0.68
entious
-0.67
POSITIVE LOGITS
eering
0.86
laureate
0.78
ocrat
0.74
enshr
0.73
ocracy
0.73
democracy
0.67
republic
0.65
democracy
0.65
uprising
0.65
reform
0.64
Activations Density 0.025%