INDEX
Explanations
references to the concept of majority in decision-making contexts
New Auto-Interp
Negative Logits
boxes
-0.91
boxes
-0.85
WARE
-0.83
bundles
-0.76
rams
-0.75
features
-0.74
gling
-0.73
encl
-0.73
snippets
-0.73
alez
-0.72
POSITIVE LOGITS
opinion
0.76
Tribal
0.75
vote
0.74
Presidency
0.71
atical
0.70
vote
0.68
Republican
0.68
truce
0.68
referendum
0.68
Democratic
0.67
Activations Density 0.040%