INDEX
Explanations
references to specific days or temporal markers associated with activities or events
New Auto-Interp
Negative Logits
orthand
-0.17
ring
-0.17
orf
-0.16
(disposing
-0.16
baum
-0.16
rice
-0.16
orc
-0.16
wu
-0.15
stag
-0.15
weg
-0.15
POSITIVE LOGITS
ton
0.28
dream
0.28
break
0.21
enu
0.21
TON
0.19
ENU
0.19
tons
0.19
-to
0.19
-day
0.18
Dream
0.18
Activations Density 0.021%