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

    Neuronpedia

    INDEX
    Explanations

    the name "ao" with varying numerical values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ao"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.84
    é¾įå¥ij士
    -0.76
    rored
    -0.71
    owship
    -0.70
    baugh
    -0.63
    ibly
    -0.63
     Hitchcock
    -0.62
     markers
    -0.62
     mathemat
    -0.62
    ÑĮ
    -0.62
    POSITIVE LOGITS
    qua
    1.12
    ÄŁ
    1.05
    zzi
    1.02
    ji
    0.93
    ao
    0.92
    pper
    0.90
    pport
    0.89
    gha
    0.88
    uthor
    0.85
    fter
    0.83
    Act Density 0.019%

    No Known Activations