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

    Neuronpedia

    INDEX
    Explanations

    quotation marks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ido
    -0.16
    IDO
    -0.15
    pez
    -0.15
    ichel
    -0.15
    帯
    -0.14
    ongyang
    -0.13
    æĭ³
    -0.13
    umat
    -0.13
    imore
    -0.13
    ******↵
    -0.13
    POSITIVE LOGITS
    ritz
    0.16
    lys
    0.15
    /apple
    0.15
     kå
    0.15
    704
    0.14
     trek
    0.14
    ána
    0.14
    ç³»
    0.14
    adoo
    0.13
    áh
    0.13
    Act Density 0.040%

    No Known Activations