INDEX
Explanations
locations and movements in physical spaces
New Auto-Interp
Negative Logits
zier
-0.14
amage
-0.14
arpa
-0.14
ÏĥÏĦά
-0.13
ίνη
-0.13
oire
-0.13
aniu
-0.13
rimp
-0.13
.Buttons
-0.13
ulong
-0.13
POSITIVE LOGITS
past
0.36
toward
0.34
towards
0.34
pursued
0.27
past
0.26
guided
0.26
dod
0.25
escorted
0.25
headed
0.24
trailed
0.24
Activations Density 0.191%