INDEX
Explanations
names of political leaders and countries
New Auto-Interp
Negative Logits
teenth
-0.90
Pyth
-0.81
ĸļ
-0.79
ively
-0.75
lv
-0.72
Asheville
-0.70
Reviewer
-0.69
runaway
-0.69
aunder
-0.68
ERA
-0.68
POSITIVE LOGITS
anyahu
1.33
Netanyahu
1.01
Jinping
0.89
stein
0.86
anca
0.83
etz
0.82
ministerial
0.79
itz
0.76
bloc
0.74
congratulated
0.72
Activations Density 0.015%