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

    Neuronpedia

    INDEX
    Explanations

    the letters "au" either as part of a word or on their own

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "au"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.63
    Wallet
    -0.63
     flares
    -0.62
    APS
    -0.61
    appers
    -0.61
    STATE
    -0.60
    orative
    -0.60
    bread
    -0.57
     Io
    -0.56
    OB
    -0.56
    POSITIVE LOGITS
    llah
    1.24
    gment
    1.08
    ction
    1.04
    qua
    0.99
    lette
    0.97
    fman
    0.93
    cel
    0.90
    ctions
    0.88
    clair
    0.88
    lly
    0.86
    Act Density 0.020%

    No Known Activations