INDEX
Explanations
references to the name "Lin" and its variations
New Auto-Interp
Negative Logits
a
-0.15
eenth
-0.15
Alive
-0.15
961
-0.14
gom
-0.14
dsn
-0.14
hete
-0.14
yı
-0.13
ante
-0.13
eva
-0.13
POSITIVE LOGITS
arity
0.20
olik
0.16
ament
0.15
oya
0.15
combe
0.15
anity
0.15
(=)
0.15
inalg
0.14
ternet
0.14
chein
0.14
Activations Density 0.017%