INDEX
Explanations
historical references to royalty and their reigns
New Auto-Interp
Negative Logits
ISE
-0.17
ilin
-0.15
417
-0.14
/apt
-0.14
443
-0.14
abit
-0.14
rlen
-0.13
idi
-0.13
598
-0.13
yll
-0.13
POSITIVE LOGITS
Charles
0.23
King
0.21
Frederick
0.19
Feder
0.19
Louis
0.19
Maxim
0.18
Henry
0.18
Queen
0.17
otto
0.17
Baldwin
0.17
Activations Density 0.085%