INDEX
Explanations
words containing special characters like "ü"
occurrences of the character "ü" in various contexts
New Auto-Interp
Negative Logits
Keeper
-0.68
fracture
-0.67
ertodd
-0.66
Seas
-0.66
ividual
-0.64
Izan
-0.64
assian
-0.63
Raider
-0.62
Eaton
-0.61
xon
-0.61
POSITIVE LOGITS
ü
1.20
¿
1.01
¶
1.00
·
0.98
¬
0.96
Ķ
0.94
ĺ
0.92
³
0.91
¸
0.91
¹
0.89
Activations Density 0.004%