INDEX
Explanations
references to "modern day" or similar phrases indicating contemporary contexts
New Auto-Interp
Negative Logits
ccione
-0.18
eteria
-0.17
feld
-0.16
erson
-0.16
ye
-0.16
andom
-0.16
/releases
-0.16
ditor
-0.15
ennen
-0.15
rist
-0.14
POSITIVE LOGITS
تا
0.16
ASI
0.15
eÄį
0.15
ToEnd
0.14
ãģ®ãĤĤ
0.14
Smarty
0.14
uration
0.14
zer
0.14
ONSE
0.13
hiba
0.13
Activations Density 0.003%