INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     U
    1.27
     B
    1.21
     T
    1.19
     N
    1.18
     J
    1.16
     R
    1.14
     
    1.12
     L
    1.10
     P
    1.06
     G
    1.06
    POSITIVE LOGITS
     βιβ
    1.45
    📚
    1.36
     libros
    1.34
     kitabı
    1.34
     книг
    1.32
    📕
    1.30
     knj
    1.27
    📗
    1.27
    books
    1.26
    選び
    1.25
    Act Density 0.421%

    No Known Activations