INDEX
Explanations
phrases indicating comparison, specifically the phrase "among other things"
references to additional information or context surrounding a subject
New Auto-Interp
Negative Logits
xit
-0.83
ĸļ
-0.82
iker
-0.80
ister
-0.79
ISTER
-0.69
hend
-0.68
Patent
-0.67
Belfast
-0.66
Bake
-0.65
INAL
-0.64
POSITIVE LOGITS
things
1.49
factors
1.18
places
1.10
Things
1.08
reasons
1.07
things
1.06
considerations
1.04
thing
1.03
topics
1.02
feats
1.00
Activations Density 0.034%