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

    Neuronpedia

    INDEX
    Explanations

    references to social issues and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    668
    -0.15
    eward
    -0.15
    /generated
    -0.15
     بÙĨدÛĮ
    -0.14
    á»ķ
    -0.14
    ãĥĹãĥª
    -0.13
    elder
    -0.13
    ãģĨãģ¡
    -0.13
    ìħĺ
    -0.13
    688
    -0.13
    POSITIVE LOGITS
    atty
    0.16
    coli
    0.15
    ationally
    0.15
    é¹
    0.15
    readcr
    0.15
    agli
    0.14
    _nh
    0.14
    ogs
    0.14
    oload
    0.14
    peak
    0.14
    Act Density 0.603%

    No Known Activations