INDEX
    Explanations

    words related to vulnerability or exposure of one's emotions

    New Auto-Interp
    Negative Logits
    riba
    -0.07
    ollipop
    -0.07
    erdale
    -0.07
    vette
    -0.06
    raphic
    -0.06
    tes
    -0.06
    phan
    -0.06
    ship
    -0.06
    sit
    -0.06
    sizeof
    -0.06
    POSITIVE LOGITS
    -toggler
    0.07
    ãĢħ
    0.07
    ầu
    0.07
    atum
    0.06
    earch
    0.06
    renc
    0.06
    achat
    0.06
    ê·Ģ
    0.06
     Nicholson
    0.06
    §
    0.06
    Act Density 0.009%

    No Known Activations