INDEX
Explanations
mentions or discussions related to legal and political matters
New Auto-Interp
Negative Logits
inar
-0.65
away
-0.64
VERT
-0.64
arn
-0.63
Quantity
-0.62
arse
-0.62
ore
-0.62
OTH
-0.62
rait
-0.61
cart
-0.61
POSITIVE LOGITS
"[
1.08
"â̦
0.96
however
0.90
"(
0.86
although
0.84
"...
0.82
"'
0.79
'[
0.79
meanwhile
0.75
there
0.75
Activations Density 0.092%