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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to "bespoke" or custom-made items and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.92
    ãĥ¼ãĥĨ
    -0.78
    ALLY
    -0.76
    ITION
    -0.70
    atorium
    -0.66
     Executive
    -0.66
    vation
    -0.66
    atory
    -0.66
    istically
    -0.64
    ISM
    -0.64
    POSITIVE LOGITS
    erker
    1.13
    iege
    1.07
    aved
    0.94
    sembly
    0.94
    eed
    0.94
    erk
    0.94
    semb
    0.94
    pect
    0.90
    esh
    0.89
    erver
    0.88
    Act Density 0.035%

    No Known Activations