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

    Neuronpedia

    INDEX
    Explanations

    terms related to oversight and examination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brook
    -0.15
    irs
    -0.15
    ehler
    -0.15
    /rem
    -0.14
    IFA
    -0.14
    osen
    -0.14
    onomy
    -0.14
    cest
    -0.14
    ango
    -0.14
    ifa
    -0.13
    POSITIVE LOGITS
    nce
    0.15
    luž
    0.15
    Ø·
    0.15
    apter
    0.14
     PREF
    0.14
     NÄĽm
    0.14
    æľĿ
    0.14
    mons
    0.13
    _topology
    0.13
    /Search
    0.13
    Act Density 0.003%

    No Known Activations