INDEX
Explanations
instances of the name "Donald" in various contexts
New Auto-Interp
Negative Logits
.WinForms
-0.16
kills
-0.16
anes
-0.15
geber
-0.14
//---------------------------------------------------------------------------↵↵
-0.14
amil
-0.14
ias
-0.14
ëģĶ
-0.14
¸ı
-0.14
plug
-0.14
POSITIVE LOGITS
son
0.30
Trump
0.27
SON
0.22
Trump
0.21
sons
0.21
sonian
0.20
trump
0.19
-Trump
0.19
Duck
0.18
nelly
0.18
Activations Density 0.008%