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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unte
    -0.17
    aight
    -0.15
    enth
    -0.15
    fect
    -0.15
    ÃŃk
    -0.15
    ĥĿ
    -0.15
    embro
    -0.14
    voje
    -0.14
    icult
    -0.14
    ücken
    -0.14
    POSITIVE LOGITS
     con
    0.15
    hoa
    0.15
    //{{
    0.15
     Locker
    0.15
    .Provider
    0.14
     undert
    0.14
    _mono
    0.14
     prob
    0.13
     king
    0.13
     the
    0.13
    Act Density 0.012%

    No Known Activations