INDEX
Explanations
political and government-related terms and actions
mentions of political events and figures
New Auto-Interp
Negative Logits
heit
-0.77
awi
-0.77
zsche
-0.76
largeDownload
-0.74
viation
-0.74
ruary
-0.73
elin
-0.73
ances
-0.71
bara
-0.71
urally
-0.71
POSITIVE LOGITS
Kavanaugh
0.98
Dems
0.94
').
0.82
]}
0.73
Senate
0.72
Replay
0.71
]);
0.70
']
0.69
];
0.68
});
0.68
Activations Density 0.090%