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

    Neuronpedia

    INDEX
    Explanations

    mention of educational institutions and professional affiliations

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.75
     incent
    -0.71
    OTHER
    -0.71
    ¥µ
    -0.69
    Higher
    -0.69
    Department
    -0.68
    ramids
    -0.67
    Otherwise
    -0.67
    Sov
    -0.67
    Translation
    -0.67
    POSITIVE LOGITS
     he
    1.06
     Mr
    0.99
     she
    0.99
     Ms
    0.86
     Rodrigo
    0.84
     Stephen
    0.83
     Colin
    0.83
     Joshua
    0.81
     Dr
    0.81
     Kevin
    0.80
    Act Density 0.191%

    No Known Activations