INDEX
    Explanations

    references to justice, support, and motivation within social contexts

    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.63
     ролях
    -0.57
    cionario
    -0.52
     enää
    -0.50
     >=",
    -0.49
    balleur
    -0.48
     שוליים
    -0.47
     clínico
    -0.47
     kollu
    -0.47
    Hentet
    -0.47
    POSITIVE LOGITS
     support
    0.37
     Ob
    0.36
    Ob
    0.35
    RTSC
    0.35
     help
    0.35
     Lessing
    0.35
    KommentareTeilen
    0.34
    ital
    0.34
     Nea
    0.34
    ρίου
    0.33
    Act Density 0.059%

    No Known Activations