INDEX
    Explanations

    references to social dynamics and influence among individuals

    New Auto-Interp
    Negative Logits
    alet
    -0.16
    ález
    -0.16
    fit
    -0.15
    uther
    -0.15
    avic
    -0.15
    vous
    -0.14
     num
    -0.14
     fit
    -0.14
    allis
    -0.14
    Ãł
    -0.14
    POSITIVE LOGITS
    åħ±
    0.16
    uids
    0.15
     COPYRIGHT
    0.15
    _party
    0.15
    ĸī
    0.15
    /shared
    0.15
    éľ
    0.14
     ÑĩÑĥж
    0.14
    Ð¡Ðł
    0.14
     Parl
    0.14
    Act Density 0.096%

    No Known Activations