INDEX
    Explanations

    expressions of emotional support and compassion

    New Auto-Interp
    Negative Logits
     Nam
    -0.16
     Gron
    -0.16
     Gor
    -0.15
    YTE
    -0.15
    esti
    -0.15
    elper
    -0.14
    iaux
    -0.14
    skb
    -0.14
     Gore
    -0.14
    ippi
    -0.14
    POSITIVE LOGITS
    ogue
    0.14
    /plugin
    0.13
    inet
    0.13
     feminine
    0.13
    omb
    0.13
    Å¡ÃŃ
    0.13
     *__
    0.13
    моÑĤ
    0.13
    .Abstract
    0.13
     cps
    0.13
    Act Density 0.137%

    No Known Activations