INDEX
Explanations
references to the name "Franklin."
New Auto-Interp
Negative Logits
oux
-0.18
actionDate
-0.17
iesen
-0.17
ochen
-0.16
å¤ĩ
-0.16
Cá»Ļng
-0.15
اخر
-0.14
داÙĨÙĦÙĪØ¯
-0.14
idon
-0.14
erland
-0.14
POSITIVE LOGITS
lin
0.20
Pierce
0.20
furt
0.19
fort
0.18
ovel
0.17
Roosevelt
0.16
rijk
0.16
raman
0.16
inton
0.16
stein
0.15
Activations Density 0.011%