INDEX
Explanations
references to individuals named William
New Auto-Interp
Negative Logits
eous
-0.16
een
-0.15
ÙİØŃ
-0.15
hower
-0.15
bout
-0.15
asaki
-0.15
eling
-0.14
elles
-0.14
BuilderInterface
-0.14
ximity
-0.14
POSITIVE LOGITS
iards
0.18
ingham
0.17
boards
0.17
son
0.17
sons
0.17
Tec
0.17
SON
0.16
sWith
0.16
ions
0.16
sville
0.16
Activations Density 0.021%