INDEX
Explanations
occurrences of the name "Doug" or variations of it
New Auto-Interp
Negative Logits
san
-0.16
rive
-0.15
song
-0.15
VML
-0.15
ichel
-0.14
매
-0.14
lh
-0.14
nis
-0.14
uco
-0.14
ers
-0.14
POSITIVE LOGITS
lass
0.33
LAS
0.24
лаÑģ
0.21
Dou
0.18
Dou
0.17
ernaut
0.17
glas
0.16
наÑĤ
0.16
ĺìĿ´
0.16
dou
0.15
Activations Density 0.008%