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

    Neuronpedia

    INDEX
    Explanations

    phrases and words emphasizing fundamental concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONO
    -0.14
    _MODULE
    -0.14
    agen
    -0.14
    apia
    -0.14
    Ìĥ
    -0.14
    sel
    -0.13
    /books
    -0.13
    ött
    -0.13
    oley
    -0.13
    bie
    -0.13
    POSITIVE LOGITS
    mente
    0.18
    597
    0.18
    /original
    0.17
    antly
    0.17
    ucker
    0.17
     underlying
    0.17
    ially
    0.17
    ìłģìľ¼ë¡ľ
    0.16
    lest
    0.16
    /core
    0.15
    Act Density 0.037%

    No Known Activations