INDEX
Explanations
prepositional phrases indicating motion or direction
New Auto-Interp
Negative Logits
bor
-0.14
consum
-0.14
RAP
-0.14
LY
-0.14
oor
-0.13
alerts
-0.13
edic
-0.13
completeness
-0.13
Home
-0.13
exh
-0.13
POSITIVE LOGITS
ÐIJÑĢÑħÑĸв
0.18
ÃĤu
0.15
erto
0.15
IPA
0.15
.utf
0.15
vip
0.14
orsch
0.14
inson
0.14
ented
0.14
iland
0.14
Activations Density 0.032%