INDEX
Explanations
mentions of individuals named Bernard or Bernie
New Auto-Interp
Negative Logits
ollapse
-0.16
елей
-0.16
atra
-0.16
angstrom
-0.15
illery
-0.15
á»Ļ
-0.14
-urlencoded
-0.14
xCF
-0.14
DownList
-0.14
éĭ
-0.13
POSITIVE LOGITS
prite
0.16
popular
0.15
nz
0.14
amel
0.14
542
0.14
001
0.14
inals
0.14
ÙĨÚ¯
0.14
static
0.13
popular
0.13
Activations Density 0.008%