INDEX
Explanations
verbs and auxiliary verbs indicating actions or states
New Auto-Interp
Negative Logits
Boeh
-0.15
ild
-0.15
FTWARE
-0.15
uco
-0.15
CLUDING
-0.14
ë²Į
-0.14
तर
-0.14
HOLDERS
-0.14
éal
-0.14
CADE
-0.14
POSITIVE LOGITS
Solo
0.17
ansk
0.15
leader
0.15
von
0.14
antry
0.14
referrer
0.14
Castro
0.14
chos
0.14
Solo
0.14
ä»ģ
0.14
Activations Density 0.002%