INDEX
    Explanations

    references to significant socio-political issues

    New Auto-Interp
    Negative Logits
    inar
    -0.16
    .yy
    -0.15
     Gron
    -0.15
    vos
    -0.14
    ville
    -0.14
    assel
    -0.14
     Fur
    -0.14
    aptive
    -0.14
    .FontStyle
    -0.14
    pler
    -0.14
    POSITIVE LOGITS
    anden
    0.19
    ưa
    0.16
    θη
    0.16
    iš
    0.15
    deaux
    0.14
    lems
    0.14
    ietf
    0.14
    ellung
    0.14
    iena
    0.14
    lec
    0.13
    Act Density 0.049%

    No Known Activations