INDEX
Explanations
verbs that indicate the initiation or commencement of an action
New Auto-Interp
Negative Logits
emin
-0.15
eph
-0.15
rimon
-0.15
antasy
-0.15
erland
-0.14
stable
-0.14
akit
-0.14
arme
-0.14
inis
-0.14
_".$
-0.14
POSITIVE LOGITS
šk
0.15
406
0.14
536
0.14
imposs
0.14
itra
0.13
val
0.13
tir
0.13
wirk
0.13
process
0.13
osaurs
0.13
Activations Density 0.077%