INDEX
Explanations
mentions of the name "David"
New Auto-Interp
Negative Logits
šit
-0.16
eru
-0.15
aveled
-0.15
.tie
-0.14
.crm
-0.14
_threads
-0.14
Structural
-0.14
Apex
-0.14
erus
-0.14
veau
-0.14
POSITIVE LOGITS
son
0.28
sons
0.25
SON
0.22
ic
0.21
sonian
0.21
Ñģон
0.21
Bowie
0.21
enko
0.19
Letter
0.18
سÙĪÙĨ
0.18
Activations Density 0.018%