INDEX
Explanations
words and phrases associated with excess or intensity, often depicting lavishness or extravagance
New Auto-Interp
Negative Logits
ensa
-0.20
ials
-0.19
gesi
-0.19
icals
-0.18
uforia
-0.17
ulton
-0.17
nationals
-0.17
-addon
-0.17
Spicer
-0.17
inals
-0.17
POSITIVE LOGITS
ous
0.34
antly
0.33
uous
0.32
ant
0.30
eous
0.29
ently
0.29
itous
0.28
ful
0.28
ulent
0.27
ely
0.27
Activations Density 0.125%