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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their context within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reesome
    -0.18
    eyi
    -0.15
    iae
    -0.15
     Shields
    -0.15
    PIO
    -0.14
    itar
    -0.14
    ThreadId
    -0.13
    erta
    -0.13
     Cas
    -0.13
    itur
    -0.13
    POSITIVE LOGITS
     adj
    0.16
    æ£ļ
    0.16
     Produkt
    0.15
    idian
    0.15
    ics
    0.14
    essional
    0.14
    _marshall
    0.14
    SetBranch
    0.14
     erotico
    0.14
     compared
    0.14
    Act Density 0.198%

    No Known Activations