INDEX
Explanations
phrases indicating time and specific durations in years related to events
New Auto-Interp
Negative Logits
azy
-0.17
vd
-0.15
itore
-0.14
Steph
-0.14
aland
-0.14
od
-0.14
mk
-0.14
ighest
-0.14
fel
-0.14
ÙħØ©
-0.14
POSITIVE LOGITS
chematic
0.15
èħ°
0.15
affe
0.15
лиÑħ
0.14
Schn
0.14
sembly
0.14
plá
0.14
ÑĢÑıд
0.14
initial
0.14
riott
0.14
Activations Density 0.109%