INDEX
Explanations
mentions of the name "Douglas" or variations of "Doug."
New Auto-Interp
Negative Logits
tg
-0.17
oog
-0.16
nis
-0.15
syn
-0.15
song
-0.15
etros
-0.15
iom
-0.14
SEQUENTIAL
-0.14
447
-0.14
essen
-0.14
POSITIVE LOGITS
lass
0.27
LAS
0.21
ernaut
0.18
лаÑģ
0.17
eldorf
0.16
Dou
0.15
glas
0.15
ipped
0.15
ĺìĿ´
0.15
åŁ
0.15
Activations Density 0.010%