INDEX
Explanations
references to situations or events with high intensity or controversy
intense emotional or controversial topics in political discourse
New Auto-Interp
Negative Logits
Norn
-0.69
yne
-0.69
cured
-0.65
ocene
-0.62
uggle
-0.60
disabled
-0.60
??
-0.59
Zelda
-0.59
ta
-0.58
Blend
-0.58
POSITIVE LOGITS
deflation
0.72
®
0.71
iliar
0.68
diplomatic
0.68
²¾
0.67
verage
0.66
odox
0.66
bureaucratic
0.65
Opposition
0.64
nec
0.63
Activations Density 0.518%