INDEX
Explanations
references to the character "Bosley" and its variations in various contexts
New Auto-Interp
Negative Logits
ghi
-0.15
oid
-0.15
estroy
-0.15
ãĥ³ãĤ°
-0.15
acey
-0.15
urent
-0.14
tod
-0.14
oids
-0.14
Doll
-0.14
349
-0.14
POSITIVE LOGITS
ļ
0.20
nia
0.18
иком
0.18
oms
0.16
hevik
0.16
avern
0.16
enville
0.16
orning
0.16
combe
0.16
ниÑİ
0.16
Activations Density 0.009%