INDEX
Explanations
the infinitive form of verbs, specifically "to" followed by another verb
New Auto-Interp
Negative Logits
illez
-0.18
PCP
-0.17
pare
-0.16
azel
-0.15
dle
-0.15
Await
-0.14
aÄŁa
-0.14
/stdc
-0.14
kus
-0.14
idas
-0.14
POSITIVE LOGITS
_OD
0.15
Tear
0.15
VD
0.14
Prior
0.14
PRI
0.14
ingu
0.14
resa
0.14
ching
0.13
hydrogen
0.13
_PRI
0.13
Activations Density 0.008%