INDEX
    Explanations

    Anthony and Antonio names

    New Auto-Interp
    Negative Logits
    س
    2.17
     in
    1.70
    ни
    1.65
    с
    1.61
    д
    1.55
    1.52
    د
    1.49
    1.43
    ने
    1.39
    ام
    1.39
    POSITIVE LOGITS
    t
    1.84
    at
    1.52
    and
    1.30
    for
    1.30
    *
    1.24
    tR
    1.07
    ture
    1.04
    led
    1.03
    ee
    1.02
    b
    1.02
    Act Density 0.016%

    No Known Activations