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

    Neuronpedia

    INDEX
    Explanations

    computer code-related terms, specifically focusing on variable names and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to coding standards and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overshadow
    -0.73
     Hutch
    -0.73
    jri
    -0.73
    ¥µ
    -0.72
    wage
    -0.71
    auga
    -0.71
    owship
    -0.70
    iversary
    -0.69
    ouched
    -0.68
     outwe
    -0.67
    POSITIVE LOGITS
    execute
    0.98
     XML
    0.78
     encoding
    0.77
    Byte
    0.76
     python
    0.76
    TAG
    0.76
     parser
    0.75
     interfaces
    0.74
     executable
    0.74
     converter
    0.73
    Act Density 0.317%

    No Known Activations