INDEX
    Explanations

    subscripts and variables

    New Auto-Interp
    Negative Logits
     miała
    1.13
    hhhh
    1.04
     hippie
    1.02
     había
    0.99
     bună
    0.98
    hhh
    0.98
     měla
    0.97
    ra
    0.96
     Chick
    0.95
    hz
    0.94
    POSITIVE LOGITS
    m
    1.27
    ت
    1.23
    م
    1.14
    SP
    0.98
    Mix
    0.97
    0.96
    м
    0.94
    yam
    0.93
    ۰
    0.90
    т
    0.89
    Act Density 0.109%

    No Known Activations