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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and groups, particularly through the use of the word "whom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.70
     pleaſure
    -0.69
     ſtre
    -0.64
    queryInterface
    -0.62
     faſt
    -0.61
    pushFollow
    -0.60
     ſtand
    -0.60
     juſ
    -0.59
     leaſt
    -0.57
     becauſe
    -0.57
    POSITIVE LOGITS
     of
    0.55
    of
    0.47
     davon
    0.45
     ofthe
    0.44
    ofa
    0.43
     Of
    0.43
    </table>
    0.41
    Cyfarwyddwr
    0.40
    </h5>
    0.40
     thereof
    0.40
    Act Density 0.698%

    No Known Activations