INDEX
    Explanations

    references to technological systems and their implications on society

    New Auto-Interp
    Negative Logits
    ãĤīãģı
    -0.16
    636
    -0.15
    piler
    -0.15
    _gold
    -0.14
    dz
    -0.14
     cal
    -0.14
    uite
    -0.14
    .volley
    -0.14
    ainter
    -0.14
    hone
    -0.14
    POSITIVE LOGITS
    fr
    0.17
     fr
    0.16
    åĩ½
    0.15
    scriptions
    0.15
    ami
    0.14
     Occ
    0.14
    gettext
    0.14
    alta
    0.14
    ument
    0.14
    vla
    0.14
    Act Density 0.025%

    No Known Activations