INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ar
    1.12
    an
    1.11
    ul
    1.10
    n
    1.08
    arın
    0.99
    urm
    0.89
    !
    0.88
    is
    0.87
    ing
    0.86
     νέα
    0.85
    POSITIVE LOGITS
    K
    1.49
     Milk
    1.43
     milk
    1.41
    Milk
    1.33
    🥛
    1.16
    B
    1.01
    д
    1.01
     Dairy
    0.99
    L
    0.99
    0.98
    Act Density 0.013%

    No Known Activations