INDEX
Explanations
references to the name "Douglas" or its variations
New Auto-Interp
Negative Logits
ivo
-0.18
.scalablytyped
-0.16
Brend
-0.16
ivas
-0.15
ngh
-0.15
ÑĦеÑĢ
-0.14
sz
-0.14
ipherals
-0.14
ruits
-0.14
nels
-0.14
POSITIVE LOGITS
glas
0.21
dou
0.18
Dou
0.18
Dou
0.18
HLT
0.18
doubling
0.16
ouz
0.15
vre
0.15
chút
0.15
excluding
0.15
Activations Density 0.005%