INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Mifflin
    0.56
    acd
    0.55
    araan
    0.54
    સમ
    0.53
    onego
    0.52
     Programmes
    0.52
    阻塞
    0.51
     приста
    0.51
    osim
    0.51
    sources
    0.50
    POSITIVE LOGITS
     ailleurs
    0.61
     мене
    0.59
     Jealous
    0.59
     Rwand
    0.58
    0.58
     waves
    0.58
     чув
    0.57
    DEPENDENCIA
    0.57
    離開
    0.57
     rencontr
    0.56
    Act Density 0.000%

    No Known Activations