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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate authorship or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    printStats
    -0.17
    #
    -0.17
    isses
    -0.17
    InParameter
    -0.17
    oader
    -0.16
    _cmos
    -0.16
    /mail
    -0.15
    ासन
    -0.15
    //{{
    -0.15
    HeaderCode
    -0.15
    POSITIVE LOGITS
    ê¹
    0.16
     sober
    0.15
    owe
    0.15
    usk
    0.15
     O
    0.14
     synchron
    0.14
     Yo
    0.14
    еÑĢг
    0.14
    s
    0.14
     Katrina
    0.14
    Act Density 0.002%

    No Known Activations