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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal restrictions and confidentiality agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohn
    -0.16
    аÑģÑĤи
    -0.15
    kili
    -0.14
     Preston
    -0.14
    .oracle
    -0.14
    uge
    -0.14
     Bundy
    -0.14
    onica
    -0.14
    _reduce
    -0.14
    Ú©ÙĨ
    -0.14
    POSITIVE LOGITS
    ictionary
    0.17
    806
    0.17
    chwitz
    0.16
    warts
    0.16
    iked
    0.15
     gag
    0.15
    720
    0.15
    frag
    0.14
    792
    0.14
    irtual
    0.14
    Act Density 0.221%

    No Known Activations