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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms related to organizations, technologies, and scientific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ctr
    -0.17
    ÑijÑĤ
    -0.14
    È
    -0.14
    osals
    -0.14
    (){}↵
    -0.14
    Ìģt
    -0.13
    ighet
    -0.13
    ITTE
    -0.13
     ("
    -0.13
    ãĤĥ
    -0.13
    POSITIVE LOGITS
    istan
    0.14
    ABC
    0.13
    Âł
    0.13
    ),
    0.13
     CCTV
    0.13
     اع
    0.13
    xiety
    0.13
    )
    0.13
     *_
    0.13
    agan
    0.13
    Act Density 0.068%

    No Known Activations