INDEX
Explanations
references to specific time periods or centuries
New Auto-Interp
Negative Logits
ause
-0.17
amp
-0.15
laus
-0.15
s
-0.15
ur
-0.14
utt
-0.14
ao
-0.14
048
-0.14
allo
-0.14
alten
-0.13
POSITIVE LOGITS
ÙħÛĮÙĦادÛĮ
0.21
-long
0.18
ìŁģ
0.17
-old
0.16
以æĿ¥
0.15
Gest
0.15
å·¦åı³
0.14
-present
0.14
arily
0.14
ASET
0.14
Activations Density 0.021%