INDEX
    Explanations

    instances of personal pronouns and expressions of personal feelings or relationships

    New Auto-Interp
    Negative Logits
    rete
    -0.14
     çĻº
    -0.14
     Tob
    -0.14
    wart
    -0.14
    gio
    -0.14
     Mickey
    -0.14
    ableView
    -0.14
    eyse
    -0.14
    ndx
    -0.14
    ainty
    -0.13
    POSITIVE LOGITS
    ustr
    0.16
    ulla
    0.15
    CREMENT
    0.15
    alking
    0.15
    VID
    0.14
    ira
    0.14
    cost
    0.14
    cal
    0.14
    uri
    0.14
     Cliff
    0.14
    Act Density 0.391%

    No Known Activations