INDEX
    Explanations

    mentions of Democratic political figures, specifically focusing on Elizabeth Warren

    New Auto-Interp
    Negative Logits
    assel
    -0.16
    ÏĢει
    -0.15
    ingles
    -0.15
    thing
    -0.14
    carrier
    -0.14
    Ù
    -0.14
    irit
    -0.14
    INTR
    -0.14
     carrier
    -0.14
    sworth
    -0.14
    POSITIVE LOGITS
    orb
    0.16
    ombres
    0.16
    缮
    0.15
    isclosed
    0.15
    ames
    0.15
    arf
    0.14
     Uint
    0.14
    ÃŃme
    0.14
    imator
    0.14
    yte
    0.14
    Act Density 0.003%

    No Known Activations