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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "ade" followed by a number, particularly "ade 9" and "ade 8"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "ade" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipeg
    -0.75
    ivity
    -0.73
    iew
    -0.72
    urers
    -0.71
    urally
    -0.70
    ship
    -0.69
     Kaufman
    -0.66
    orem
    -0.66
    igration
    -0.65
    atem
    -0.64
    POSITIVE LOGITS
    lled
    0.89
    utic
    0.77
    hani
    0.75
    hyde
    0.73
    vice
    0.72
    lda
    0.72
    pee
    0.71
    ع
    0.70
    lla
    0.70
    rers
    0.70
    Act Density 0.025%

    No Known Activations