INDEX
Explanations
references to Apple products, specifically iPhones and iPads
New Auto-Interp
Negative Logits
ÑģÑı
-0.19
ly
-0.19
uchsia
-0.15
andro
-0.15
Richardson
-0.15
geh
-0.15
hn
-0.14
ت
-0.14
eted
-0.14
cut
-0.14
POSITIVE LOGITS
/i
0.25
/ip
0.23
ography
0.18
6
0.17
7
0.17
XS
0.17
SE
0.17
5
0.17
xs
0.16
|i
0.16
Activations Density 0.009%