INDEX
Explanations
references to historical texts and their descriptions
New Auto-Interp
Negative Logits
alborg
-0.16
COPYRIGHT
-0.16
straction
-0.16
ovice
-0.15
Lords
-0.15
umas
-0.14
okable
-0.14
.writ
-0.14
Writes
-0.13
#+
-0.13
POSITIVE LOGITS
phil
0.25
editions
0.22
pale
0.22
edition
0.20
edition
0.20
Transmission
0.20
Corpus
0.20
Transmission
0.20
Supplements
0.19
Edition
0.19
Activations Density 0.109%