INDEX
Explanations
occurrences of the name "Dani" or its variations
New Auto-Interp
Negative Logits
wick
-0.17
ngen
-0.16
okus
-0.16
/commons
-0.16
gend
-0.15
mons
-0.15
ushima
-0.15
fen
-0.15
athan
-0.14
ichert
-0.14
POSITIVE LOGITS
ela
0.27
ells
0.21
elsen
0.21
elle
0.21
ella
0.20
il
0.20
iele
0.19
èle
0.18
ÙĬÙĦا
0.18
å¤
0.17
Activations Density 0.018%