INDEX
Explanations
phrases indicating a change in status or progression
occurrences of the phrase "now that" in various contexts
New Auto-Interp
Negative Logits
;;;;
-0.75
oen
-0.73
igmatic
-0.68
ascript
-0.67
HOW
-0.66
teasp
-0.66
iege
-0.65
æ©
-0.63
pring
-0.62
krit
-0.60
POSITIVE LOGITS
we
1.00
's
0.94
you
0.75
they
0.74
seems
0.72
happens
0.70
rely
0.69
he
0.68
settles
0.66
hasn
0.64
Activations Density 0.084%