INDEX
Explanations
occurrences of the word "by" in various contexts, indicating authorship or attribution
New Auto-Interp
Negative Logits
ſche
-0.72
IsContent
-0.71
pleaſure
-0.69
Diſ
-0.65
houſe
-0.63
ſtate
-0.62
ollectionView
-0.61
ſtre
-0.60
faſt
-0.59
iſt
-0.59
POSITIVE LOGITS
oleh
1.05
by
1.04
by
0.98
By
0.93
By
0.89
BY
0.76
ידי
0.75
द्वारा
0.74
بواسطة
0.73
geslacht
0.73
Activations Density 0.144%