INDEX
Explanations
information related to politicians and political events
references to specific individuals and their political roles
New Auto-Interp
Negative Logits
ulia
-0.88
Entry
-0.65
=-=-=-=-=-=-=-=-
-0.64
glers
-0.64
gart
-0.63
eric
-0.60
kai
-0.59
CST
-0.59
cules
-0.59
goo
-0.58
POSITIVE LOGITS
esson
0.76
avanaugh
0.71
Trump
0.64
Ford
0.64
Chair
0.62
asse
0.62
iden
0.62
Senate
0.61
ixel
0.58
true
0.58
Activations Density 0.059%