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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a particular country or place

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "va" which likely relates to a specific identifier or classification within a context (possibly referring to variables or entities in a system)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cases
    -0.79
    papers
    -0.77
    dress
    -0.76
    brow
    -0.71
    taker
    -0.71
    sworth
    -0.70
    wolves
    -0.70
    lins
    -0.70
    liners
    -0.69
    sticks
    -0.69
    POSITIVE LOGITS
     Scotia
    0.97
    Äį
    0.95
    ignt
    0.89
    uthor
    0.89
     Hels
    0.88
    qua
    0.87
    ille
    0.87
    quez
    0.87
    ices
    0.79
    apor
    0.79
    Act Density 0.010%

    No Known Activations