INDEX
Explanations
mentions of different iPhone and iPad models
New Auto-Interp
Negative Logits
yun
-0.16
.coll
-0.15
grav
-0.15
deen
-0.15
indow
-0.15
lix
-0.15
ex
-0.14
isz
-0.14
ز
-0.14
piv
-0.14
POSITIVE LOGITS
SE
0.21
SE
0.20
XR
0.18
XR
0.18
XS
0.18
XS
0.17
nano
0.15
-xs
0.15
ography
0.15
Nano
0.15
Activations Density 0.007%