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

    Neuronpedia

    INDEX
    Explanations

    names of locations or people ending with "bar."

    oai_token-act-pair · gpt-3.5-turbo

    words containing the substring "bar" or "har"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.80
    lect
    -0.75
    urally
    -0.70
    serv
    -0.69
    htaking
    -0.69
    erv
    -0.68
    urer
    -0.67
    uring
    -0.66
    erm
    -0.66
    erver
    -0.66
    POSITIVE LOGITS
    aja
    0.98
    rier
    0.89
    neau
    0.88
    geon
    0.87
    allel
    0.83
    apter
    0.82
    ror
    0.82
    ration
    0.80
    anic
    0.79
    assment
    0.77
    Act Density 0.054%

    No Known Activations