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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    retty
    -0.15
    orde
    -0.15
    ounge
    -0.15
    erald
    -0.14
     prostitutas
    -0.14
    ourse
    -0.14
    cade
    -0.14
    rouch
    -0.14
    boru
    -0.14
    acob
    -0.13
    POSITIVE LOGITS
    owitz
    0.15
    949
    0.14
    авиÑģ
    0.14
    vier
    0.14
    é±
    0.14
    anje
    0.13
     Georges
    0.13
    uras
    0.13
    zano
    0.13
     Bom
    0.13
    Act Density 0.229%

    No Known Activations