INDEX
Explanations
mentions of the name "David."
New Auto-Interp
Negative Logits
ums
-0.17
алеж
-0.16
ÑĢование
-0.15
ãĥ¼ãĥ³
-0.15
oge
-0.15
iffer
-0.15
Porno
-0.15
âĹĦ
-0.15
ToPoint
-0.14
_codegen
-0.14
POSITIVE LOGITS
Bowie
0.29
Duch
0.17
Lynch
0.16
iná
0.16
Crosby
0.15
ÏĥÏį
0.15
Bow
0.15
Copper
0.15
bow
0.14
ainty
0.14
Activations Density 0.012%