INDEX
    Explanations

    prominent themes and elements related to comedy and political discourse

    New Auto-Interp
    Negative Logits
    asca
    -0.15
    ernal
    -0.15
    cü
    -0.13
    ãĤŃãĥ¥
    -0.13
     Mountains
    -0.13
    éĻ¢
    -0.13
    ede
    -0.13
     Vie
    -0.13
    Lifetime
    -0.13
    Deal
    -0.12
    POSITIVE LOGITS
    axe
    0.17
    caf
    0.14
    .bam
    0.14
    _FAR
    0.14
    utow
    0.14
    å¿Ĺ
    0.14
     ÑĩиÑģ
    0.14
    nov
    0.14
    outer
    0.13
    aren
    0.13
    Act Density 0.004%

    No Known Activations