INDEX
Explanations
strong verbs indicating actions and significant changes
New Auto-Interp
Negative Logits
able
-0.19
ordo
-0.17
/by
-0.16
zed
-0.15
zzo
-0.14
essed
-0.14
äºĨ
-0.14
è
-0.14
blink
-0.14
oster
-0.14
POSITIVE LOGITS
/is
0.25
yesterday
0.22
бÑĭ
0.21
originally
0.19
iate
0.19
nt
0.19
ness
0.18
rale
0.18
earlier
0.18
ÅĽmy
0.18
Activations Density 1.264%