INDEX
Explanations
words with a specific accent or symbol "ÃŃ"
the presence of a specific character or symbol in text
New Auto-Interp
Negative Logits
uyomi
-0.73
owed
-0.72
enegger
-0.68
Perkins
-0.66
buckle
-0.65
Seah
-0.64
surv
-0.63
Sussex
-0.63
Downloadha
-0.63
guiActiveUnfocused
-0.63
POSITIVE LOGITS
ÃŃ
0.95
¢
0.92
ð
0.87
nai
0.86
á
0.80
Ãī
0.80
Å
0.79
lean
0.79
Äį
0.78
ón
0.77
Activations Density 0.010%