INDEX
Explanations
occurrences of the word "prince" in various formats and contexts
New Auto-Interp
Negative Logits
illow
-0.47
utafitiHapana
-0.46
retudo
-0.44
iomanip
-0.44
fatos
-0.41
gehad
-0.41
wystarczy
-0.40
DataAnnotations
-0.40
зру
-0.39
requipa
-0.39
POSITIVE LOGITS
prince
1.16
Prince
1.15
Prince
1.09
prince
1.03
PRINCE
1.00
princes
0.88
Princes
0.85
Prinz
0.79
INCE
0.78
príncipe
0.74
Activations Density 0.004%