INDEX
Explanations
mentions of the name "Lore" and its variations
New Auto-Interp
Negative Logits
--------------↵
-0.15
rieg
-0.15
Kurd
-0.15
ending
-0.14
izio
-0.14
rant
-0.14
iams
-0.14
rief
-0.14
riba
-0.14
rene
-0.14
POSITIVE LOGITS
lla
0.26
ll
0.21
lli
0.20
ctal
0.20
llen
0.19
Ìģ
0.18
ns
0.18
tti
0.18
nce
0.18
gon
0.18
Activations Density 0.028%