INDEX
Explanations
the name "James" in various contexts
New Auto-Interp
Negative Logits
atti
-0.15
swick
-0.15
illow
-0.15
sert
-0.14
elier
-0.14
itemprop
-0.14
rezent
-0.14
Äįin
-0.14
ìłĢ
-0.14
omer
-0.14
POSITIVE LOGITS
stown
0.21
son
0.21
iana
0.19
sons
0.19
anta
0.18
burg
0.17
atan
0.17
SON
0.16
stones
0.16
lee
0.16
Activations Density 0.186%