INDEX
Explanations
the presence of the name "Owen" or related variants
New Auto-Interp
Negative Logits
amo
-0.15
porter
-0.15
amon
-0.15
_callbacks
-0.15
doch
-0.14
.unpack
-0.14
zioni
-0.14
IMITIVE
-0.14
UMENT
-0.14
yar
-0.14
POSITIVE LOGITS
igth
0.17
adh
0.17
anke
0.16
Ih
0.16
.vaadin
0.16
leigh
0.15
igar
0.15
ylie
0.15
Fist
0.15
enny
0.15
Activations Density 0.007%