INDEX
    Explanations

    references to fundraising events, particularly for cancer research

    New Auto-Interp
    Negative Logits
     kino
    -0.16
     Democracy
    -0.15
    achten
    -0.15
    ardu
    -0.15
    odesk
    -0.14
     Welfare
    -0.14
    Bullet
    -0.14
    éϰ
    -0.14
    rina
    -0.14
    nuts
    -0.14
    POSITIVE LOGITS
     Cure
    0.21
     Pink
    0.20
     pink
    0.19
     cure
    0.18
     walks
    0.17
    Pink
    0.17
     Colon
    0.16
     colon
    0.16
     aff
    0.16
    Walk
    0.16
    Act Density 0.056%

    No Known Activations