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

    Neuronpedia

    INDEX
    Explanations

    references to judicial titles or roles, specifically "Justice" and "Justices."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Sven
    -0.71
     Ferdinando
    -0.71
     Eileen
    -0.69
    adə
    -0.69
     Olga
    -0.67
    Sven
    -0.67
     Peggy
    -0.65
    ไง
    -0.64
    Peggy
    -0.62
    ="#"
    -0.61
    POSITIVE LOGITS
     Justice
    1.38
    Justice
    1.27
     Justices
    1.27
     justices
    1.27
     JUSTICE
    1.27
     justice
    1.13
    justice
    1.11
     Justiz
    0.85
    Jus
    0.81
    twimg
    0.81
    Act Density 0.014%

    No Known Activations