INDEX
Explanations
references to the name "Yol" and variations of it, indicating a focus on that specific term
New Auto-Interp
Negative Logits
esis
-0.23
umu
-0.20
ibbon
-0.19
esco
-0.18
em
-0.18
eel
-0.17
dialogs
-0.17
etti
-0.17
ess
-0.17
äll
-0.17
POSITIVE LOGITS
phe
0.20
ateral
0.19
itics
0.19
monary
0.18
utions
0.18
li
0.18
ambda
0.18
llll
0.18
olo
0.18
r
0.17
Activations Density 0.067%