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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Anne."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yz
    -0.81
    ODUCT
    -0.75
    oted
    -0.74
    istani
    -0.73
    ivated
    -0.72
    ramid
    -0.72
    notes
    -0.72
    ornia
    -0.71
    oter
    -0.70
     sidx
    -0.70
    POSITIVE LOGITS
    Marie
    1.17
     Marie
    1.14
     Hath
    1.10
     Thatcher
    1.05
     Louise
    0.93
     Anne
    0.93
     Rice
    0.89
    Anne
    0.88
     Wynne
    0.87
     Helen
    0.87
    Act Density 0.048%

    No Known Activations