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

    Neuronpedia

    INDEX
    Explanations

    personal names and surnames, potentially of public figures

    oai_token-act-pair · gpt-3.5-turbo

    names of people or personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intendent
    -0.75
    Reviewer
    -0.73
    stown
    -0.72
    ruary
    -0.72
    Äĩ
    -0.72
    rawdownloadcloneembedreportprint
    -0.70
    dylib
    -0.70
     Hurricanes
    -0.67
     LIA
    -0.65
    inations
    -0.65
    POSITIVE LOGITS
    isner
    0.67
    ravis
    0.62
    amoto
    0.60
    asma
    0.60
     vacuum
    0.59
    acher
    0.57
     lawy
    0.57
    ioxide
    0.57
    İ
    0.56
    enty
    0.56
    Act Density 0.228%

    No Known Activations