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

    Neuronpedia

    INDEX
    Explanations

    keywords related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ary"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arsity
    -0.69
    INESS
    -0.64
     DRAG
    -0.61
    ierrez
    -0.60
    aciously
    -0.59
    ources
    -0.59
    ERC
    -0.58
    externalActionCode
    -0.58
    ourced
    -0.57
    Tes
    -0.56
    POSITIVE LOGITS
    ng
    0.92
    otic
    0.77
    gian
    0.77
    chev
    0.74
    cia
    0.74
    Å«
    0.74
    hammer
    0.73
    pak
    0.73
    tarians
    0.73
    nda
    0.72
    Act Density 0.018%

    No Known Activations