INDEX
Explanations
references to the name "Simon" in various contexts
New Auto-Interp
Negative Logits
ernen
-0.15
acin
-0.15
enburg
-0.15
VL
-0.15
ennes
-0.14
aign
-0.14
uffers
-0.14
ataire
-0.14
Vz
-0.14
Silva
-0.14
POSITIVE LOGITS
cy
0.16
isable
0.15
REFERRED
0.15
icense
0.15
urm
0.14
emma
0.14
izedName
0.14
ises
0.14
ATTERN
0.14
oeff
0.14
Activations Density 0.006%