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

    Neuronpedia

    INDEX
    Explanations

    terms related to the collection of data

    oai_token-act-pair · gpt-3.5-turbo

    words related to data collection and acquisition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RET
    -0.75
    cipled
    -0.71
    cise
    -0.67
    ierre
    -0.67
    atever
    -0.63
    otta
    -0.62
    Pur
    -0.62
    uala
    -0.61
    itte
    -0.61
    coat
    -0.59
    POSITIVE LOGITS
     by
    0.80
     therein
    0.80
    abouts
    0.74
     abroad
    0.72
    swick
    0.71
    Ĥİ
    0.70
    ocument
    0.70
     previously
    0.70
     BY
    0.69
    gements
    0.69
    Act Density 0.224%

    No Known Activations