INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    f
    1.08
    t
    1.05
    ע
    0.92
    v
    0.79
    ק
    0.73
    IB
    0.72
    ה
    0.70
    SI
    0.66
    ě
    0.66
    LY
    0.64
    POSITIVE LOGITS
    م
    0.81
    to
    0.76
    СТИ
    0.76
    وم
    0.75
    ни
    0.74
    >
    0.73
    м
    0.72
    дзі
    0.71
    0.71
    onCreate
    0.69
    Act Density 0.001%

    No Known Activations