INDEX
Explanations
mentions of the name "John."
New Auto-Interp
Negative Logits
éĢļ
-0.16
indr
-0.15
kowski
-0.15
chin
-0.14
Kirk
-0.14
Cons
-0.14
.createFrom
-0.14
озÑı
-0.14
reeze
-0.14
astrology
-0.14
POSITIVE LOGITS
ORTH
0.17
cio
0.16
Plate
0.16
_reload
0.16
Bolton
0.15
ÙħÙĪØ¯
0.15
914
0.15
het
0.14
ung
0.14
Glover
0.14
Activations Density 0.024%