INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Malibu
    0.51
     Hawk
    0.50
     hawk
    0.50
     Myrtle
    0.50
     cool
    0.47
     cliff
    0.47
     Jerome
    0.47
     sticky
    0.46
     Radcliffe
    0.46
     ihe
    0.45
    POSITIVE LOGITS
    ار
    0.62
    وس
    0.60
    ق
    0.60
    origins
    0.58
     rezultat
    0.56
    t
    0.56
    هی
    0.55
    ت
    0.55
    0.54
    abilità
    0.54
    Act Density 0.000%

    No Known Activations