INDEX
Explanations
mentions of the name "Dave"
New Auto-Interp
Negative Logits
wine
-0.16
isper
-0.15
ancel
-0.15
stinence
-0.14
Crom
-0.14
ors
-0.14
Subviews
-0.14
:;↵
-0.14
mile
-0.14
isse
-0.14
POSITIVE LOGITS
y
0.30
yh
0.17
resi
0.17
yp
0.17
igh
0.16
yb
0.16
yd
0.16
ej
0.15
RIPT
0.15
eo
0.15
Activations Density 0.007%