Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cohn
    -0.70
    Pen
    -0.66
     inward
    -0.64
     lesbian
    -0.63
     lesbians
    -0.63
     Lesbian
    -0.63
     Abortion
    -0.63
     multiplied
    -0.61
    abel
    -0.60
    Anim
    -0.59
    POSITIVE LOGITS
    ĪĴ
    0.86
    İĭ
    0.79
    FTWARE
    0.76
    urst
    0.76
     Commodore
    0.75
    intosh
    0.69
    uilt
    0.69
    £ı
    0.69
    ansom
    0.67
    ¿½
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.