INDEX
Explanations
quotes, proverbs, or commonly repeated phrases
common sayings or proverbs
New Auto-Interp
Negative Logits
jri
-0.80
actions
-0.76
ressive
-0.74
osponsors
-0.73
endars
-0.72
ensibly
-0.70
orate
-0.69
viol
-0.68
ktop
-0.67
appointments
-0.67
POSITIVE LOGITS
proverb
1.24
aph
0.98
motto
0.89
wisdom
0.88
coined
0.85
cliché
0.81
uttered
0.81
mantra
0.79
rhy
0.78
lyric
0.76
Activations Density 0.261%