INDEX
Explanations
instances of repeated syllables or sounds within words
New Auto-Interp
Negative Logits
edo
-0.16
eda
-0.15
ullivan
-0.15
unker
-0.14
igned
-0.14
.enterprise
-0.14
partially
-0.14
leur
-0.14
SI
-0.13
sei
-0.13
POSITIVE LOGITS
s
0.18
OLA
0.15
inher
0.14
shit
0.14
KO
0.14
amma
0.14
abet
0.14
gle
0.14
Ñľ
0.14
rig
0.13
Activations Density 0.011%