INDEX
    Explanations

    expressions related to emotional states and interpersonal relationships

    New Auto-Interp
    Negative Logits
    enal
    -0.15
    aylor
    -0.15
    ohen
    -0.14
    klä
    -0.14
     phiếu
    -0.14
    tas
    -0.14
    ieving
    -0.14
    bei
    -0.14
    екÑĥ
    -0.13
     Kostenlose
    -0.13
    POSITIVE LOGITS
    Spell
    0.17
    spell
    0.17
     Jones
    0.16
    ringe
    0.14
    Jones
    0.14
     Controls
    0.14
     Spell
    0.14
     IMessage
    0.14
     caps
    0.14
     Bor
    0.13
    Act Density 0.175%

    No Known Activations