INDEX
Explanations
occurrences of the Chinese character "的"
New Auto-Interp
Negative Logits
Majefty
-0.97
fhew
-0.92
raiſ
-0.90
myſelf
-0.88
himſelf
-0.88
themſelves
-0.88
avoient
-0.87
chofe
-0.84
BeginContext
-0.84
Anſ
-0.83
POSITIVE LOGITS
的
1.01
s
0.96
の
0.83
'].'
0.78
peutic
0.77
thenes
0.77
의
0.76
斯的
0.75
れの
0.74
0.74
Activations Density 0.013%