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

    Neuronpedia

    INDEX
    Explanations

    references to hyperlinks in web text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "a" appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMY
    -0.61
    lining
    -0.58
     Indigo
    -0.57
     inheritance
    -0.56
    mble
    -0.56
     Lans
    -0.55
    cong
    -0.55
    hands
    -0.55
    lip
    -0.55
     EVs
    -0.55
    POSITIVE LOGITS
     href
    1.50
    aron
    0.85
    ria
    0.85
    vertisement
    0.77
    >]
    0.73
    BILITIES
    0.70
    oba
    0.70
    actionDate
    0.70
    >>
    0.69
    Prev
    0.68
    Act Density 0.012%

    No Known Activations