INDEX
Explanations
references to specific time periods, particularly the 21st century
New Auto-Interp
Negative Logits
nap
-0.20
aga
-0.19
itter
-0.17
anton
-0.16
ÙĪÙĨا
-0.16
åŃĺäºİ
-0.15
antan
-0.15
alth
-0.15
ég
-0.14
eso
-0.14
POSITIVE LOGITS
θι
0.17
-ÐŁÐµÑĤеÑĢб
0.17
PW
0.16
modern
0.16
ollider
0.16
oq
0.15
incerely
0.14
лиÑĪком
0.14
nech
0.14
(pc
0.14
Activations Density 0.023%