INDEX
Explanations
references to the name "Lincoln" in various contexts
New Auto-Interp
Negative Logits
ings
-0.17
enheim
-0.15
ges
-0.15
ture
-0.15
ele
-0.15
evin
-0.15
ei
-0.14
AGR
-0.14
ye
-0.14
positories
-0.14
POSITIVE LOGITS
shire
0.28
ite
0.20
ian
0.20
ista
0.19
ization
0.18
ized
0.17
ites
0.17
mites
0.17
aires
0.16
ÏĦαι
0.16
Activations Density 0.020%