INDEX
    Explanations

    prominent mentions of news media and their personalities

    New Auto-Interp
    Negative Logits
    uluk
    -0.06
    pta
    -0.06
     blind
    -0.06
    ẩu
    -0.06
    -radio
    -0.06
    -Semit
    -0.06
    .appspot
    -0.06
    ISCO
    -0.05
    SF
    -0.05
    uner
    -0.05
    POSITIVE LOGITS
    yi
    0.07
    -CP
    0.06
    OWN
    0.06
    agrams
    0.06
     Atlanta
    0.06
     anchor
    0.06
     network
    0.06
    inclu
    0.06
    askell
    0.06
    GX
    0.06
    Act Density 0.031%

    No Known Activations