INDEX
    Explanations

    The neuron responds to mentions of celebrity proper names (e.g., Selena Gomez, Taylor Swift, Justin Bieber).

    New Auto-Interp
    Negative Logits
    _Internal
    -0.07
    vertex
    -0.07
     WK
    -0.06
    wang
    -0.06
     موس
    -0.06
     ilgili
    -0.06
    -Semitism
    -0.06
    isVisible
    -0.06
    services
    -0.06
    OptionsMenu
    -0.06
    POSITIVE LOGITS
     कट
    0.07
     Bieber
    0.07
    ’,
    0.07
    ’.
    0.06
     guidelines
    0.06
     policies
    0.06
    .Offset
    0.06
    .BACK
    0.06
    _REPO
    0.06
    سانی
    0.06
    Act Density 0.005%

    No Known Activations