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

    Neuronpedia

    INDEX
    Explanations

    the name "Doris" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dor" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.62
     Malone
    -0.61
     uncomp
    -0.61
    HER
    -0.60
    Quotes
    -0.60
     disparate
    -0.60
     Fract
    -0.58
     congr
    -0.58
    ãĢ
    -0.57
     unheard
    -0.56
    POSITIVE LOGITS
    chester
    1.32
    fman
    1.18
    othe
    1.15
    cas
    1.11
    sey
    1.10
    oshenko
    1.06
    je
    1.02
    wyn
    1.00
    rance
    0.97
    bage
    0.96
    Act Density 0.022%

    No Known Activations