INDEX
    Explanations

    geographical names and places

    New Auto-Interp
    Negative Logits
    ellow
    -0.07
     otherwise
    -0.07
    omal
    -0.07
    otherwise
    -0.07
    Ell
    -0.07
    alm
    -0.07
    ames
    -0.07
    alam
    -0.07
    CAM
    -0.07
    amble
    -0.07
    POSITIVE LOGITS
    avra
    0.07
    529
    0.07
    ripp
    0.07
    APPER
    0.07
    IPPING
    0.06
    ennifer
    0.06
    586
    0.06
    oodle
    0.06
    apper
    0.06
    aos
    0.06
    Act Density 0.034%

    No Known Activations