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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a history of performance or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    843
    -0.16
     Class
    -0.15
    943
    -0.14
    sterol
    -0.14
    elson
    -0.14
    aravel
    -0.14
     Hat
    -0.14
    643
    -0.14
    onia
    -0.14
    Ä
    -0.14
    POSITIVE LOGITS
    -scrollbar
    0.16
     precedent
    0.15
    okies
    0.14
     Russo
    0.14
    TEGER
    0.14
    atum
    0.14
    ãİ¡
    0.14
    à¸ģารà¸ŀ
    0.13
    -LAST
    0.13
    ascus
    0.13
    Act Density 0.011%

    No Known Activations