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

    Neuronpedia

    INDEX
    Explanations

    numeric values mixed with special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the year "2007" and symbols indicating fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.82
    andom
    -0.77
    APH
    -0.75
    ¿½
    -0.74
    hyde
    -0.73
    axy
    -0.70
    ument
    -0.70
    ATES
    -0.68
    xtap
    -0.66
    phas
    -0.66
    POSITIVE LOGITS
    lers
    0.82
    lishes
    0.80
    esville
    0.79
    iership
    0.77
    herry
    0.77
    elsius
    0.77
    lished
    0.76
    iano
    0.75
    icut
    0.73
    rir
    0.72
    Act Density 0.096%

    No Known Activations