INDEX
    Explanations

    references to visual imagery and descriptive features

    New Auto-Interp
    Negative Logits
    ameda
    -0.15
     Twilight
    -0.15
    423
    -0.15
     skimage
    -0.14
    409
    -0.14
    adius
    -0.14
    ppy
    -0.14
     McMaster
    -0.14
     built
    -0.14
    uid
    -0.14
    POSITIVE LOGITS
     sinister
    0.24
     Dexter
    0.23
     argent
    0.23
     quarterly
    0.21
    zure
    0.21
     Supporters
    0.20
     charges
    0.20
    azon
    0.20
    argent
    0.20
     azure
    0.20
    Act Density 0.012%

    No Known Activations