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

    Neuronpedia

    INDEX
    Explanations

    instances of significant examples or case studies that illustrate broader concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¯ãģļ
    -0.14
    _iff
    -0.12
    ÄĻż
    -0.12
    stoup
    -0.12
    isser
    -0.12
    ught
    -0.11
    ÃŃÅ¡
    -0.11
    iphy
    -0.11
    аÑİ
    -0.11
    strument
    -0.11
    POSITIVE LOGITS
     example
    0.96
     examples
    0.88
    example
    0.77
     Example
    0.73
    examples
    0.72
     exemple
    0.71
     Examples
    0.71
    ä¾ĭ
    0.70
    -example
    0.69
     пÑĢимеÑĢ
    0.69
    Act Density 0.431%

    No Known Activations