INDEX
Explanations
mentions of political representatives and their titles
New Auto-Interp
Negative Logits
pine
-0.15
pped
-0.14
ooth
-0.14
ryn
-0.14
#Region
-0.14
Vec
-0.14
EMENT
-0.14
anker
-0.14
annes
-0.13
-spot
-0.13
POSITIVE LOGITS
-elect
0.17
candidate
0.16
Candidate
0.15
Elect
0.15
ubl
0.15
elect
0.15
elect
0.14
ÙħÙĨت
0.14
ousel
0.14
candidate
0.14
Activations Density 0.023%