INDEX
Explanations
mentions of political figures, specifically focusing on the word "Cheney"
references to specific political figures, particularly Dick Cheney and related political terminology
New Auto-Interp
Negative Logits
aan
-0.79
Torrent
-0.69
sembly
-0.67
iculture
-0.67
Ultron
-0.67
tering
-0.66
lightsaber
-0.65
icably
-0.65
į
-0.63
lihood
-0.62
POSITIVE LOGITS
Cheney
0.91
ervative
0.89
enegger
0.84
ERN
0.79
itect
0.70
memos
0.70
intosh
0.70
ervatives
0.68
rador
0.68
rolet
0.67
Activations Density 0.049%