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

    Neuronpedia

    INDEX
    Explanations

    special characters or code snippets with specific patterns

    oai_token-act-pair · gpt-3.5-turbo

    code snippets or programming-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.92
     mathemat
    -0.74
     paran
    -0.71
     Sau
    -0.70
     toile
    -0.70
     ambassadors
    -0.68
     puberty
    -0.67
    hement
    -0.67
    terday
    -0.66
     Manit
    -0.66
    POSITIVE LOGITS
    };
    1.27
    """
    1.07
    Output
    1.05
    */
    1.04
    ERROR
    0.96
    &&
    0.96
    ================
    0.95
    @@
    0.94
    Definition
    0.94
    /*
    0.94
    Act Density 0.120%

    No Known Activations