INDEX
Explanations
names of political figures
names of prominent political figures
New Auto-Interp
Negative Logits
uay
-0.81
ivity
-0.80
LESS
-0.79
alde
-0.76
azines
-0.75
ging
-0.72
icio
-0.71
roots
-0.71
ificial
-0.70
UES
-0.70
POSITIVE LOGITS
Osborne
0.91
hiba
0.80
£
0.80
Lans
0.68
ECD
0.67
bailed
0.64
Papers
0.63
forth
0.63
erella
0.62
coe
0.61
Activations Density 0.024%