INDEX
Explanations
references to physical actions and movements, particularly in relation to interactions and environments
New Auto-Interp
Negative Logits
vern
-0.18
åŀ
-0.16
seys
-0.15
eniz
-0.14
ouz
-0.14
åĨł
-0.14
gii
-0.14
esl
-0.14
нова
-0.14
.messaging
-0.13
POSITIVE LOGITS
ju
0.20
av
0.16
apl
0.15
filtr
0.15
Shepard
0.15
wich
0.15
iken
0.14
Pet
0.14
pet
0.14
ap
0.14
Activations Density 1.413%