INDEX
    Explanations

    words associated with spitting or acts of aggression

    New Auto-Interp
    Negative Logits
    uali
    -0.16
    lest
    -0.15
     ki
    -0.15
    od
    -0.14
     Conflict
    -0.14
    .encoding
    -0.14
     conflicts
    -0.14
    ulture
    -0.14
    ÑĬ
    -0.14
    ead
    -0.14
    POSITIVE LOGITS
    /WebAPI
    0.16
    PELL
    0.16
    term
    0.15
    shint
    0.15
    ERCHANT
    0.15
    .Secret
    0.15
    izza
    0.15
    lisi
    0.15
     Robbins
    0.15
     Ces
    0.15
    Act Density 0.020%

    No Known Activations