INDEX
    Explanations

    mentions of Harvey Weinstein and related political discussions

    New Auto-Interp
    Negative Logits
    oner
    -0.15
    eman
    -0.14
    dev
    -0.14
     Dispatch
    -0.14
    xb
    -0.14
    territ
    -0.14
    lesh
    -0.14
    asket
    -0.14
     Kah
    -0.13
     Tags
    -0.13
    POSITIVE LOGITS
    одо
    0.18
    addColumn
    0.15
    otos
    0.15
    ì©
    0.14
    ึà¸ĩ
    0.14
    าะ
    0.14
    Ïģιο
    0.14
    adf
    0.14
    Lint
    0.14
    quila
    0.14
    Act Density 0.001%

    No Known Activations