INDEX
Explanations
verbs indicating a state of being or existence
New Auto-Interp
Negative Logits
baum
-0.18
ály
-0.17
nett
-0.15
rette
-0.15
sville
-0.14
itive
-0.14
arts
-0.14
renc
-0.14
çͰ
-0.14
æĬŀ
-0.14
POSITIVE LOGITS
fh
0.17
chied
0.15
rott
0.15
IBE
0.14
feeding
0.14
ODEV
0.14
enko
0.14
alm
0.14
ïĢ
0.14
rah
0.14
Activations Density 0.122%