INDEX
Negative Logits
ynn
-0.18
sei
-0.17
aise
-0.17
cis
-0.16
macros
-0.16
riter
-0.15
.fun
-0.15
ilim
-0.15
eldon
-0.15
Macro
-0.14
POSITIVE LOGITS
lap
0.16
mdir
0.15
alone
0.15
bern
0.14
ntl
0.14
ani
0.14
abler
0.14
تÙĬ
0.14
оÑĢоÑĪ
0.14
æĽ²
0.13
Activations Density 0.002%