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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities, particularly related to legal or bureaucratic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schme
    -0.80
     Ser
    -0.79
     Datos
    -0.74
     Shal
    -0.73
    Ser
    -0.71
    lename
    -0.70
    SUNG
    -0.70
    eme
    -0.70
     Bateman
    -0.69
    eckel
    -0.69
    POSITIVE LOGITS
    (!__
    0.87
    })));
    0.82
    */}
    0.82
    "]];
    0.79
    CppMethod
    0.76
    %");
    0.76
    UnsafeEnabled
    0.76
    `),
    0.75
     Nagasaki
    0.74
    "]),
    0.74
    Act Density 0.693%

    No Known Activations