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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly sources or academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orn
    -0.15
    é½
    -0.15
    arem
    -0.14
     Lucas
    -0.14
    worm
    -0.14
    usage
    -0.14
    ÅĤad
    -0.14
    ocator
    -0.14
     Marsh
    -0.14
    ington
    -0.14
    POSITIVE LOGITS
    stin
    0.17
    esson
    0.15
    zes
    0.14
    کارÛĮ
    0.14
    ipa
    0.14
    onomy
    0.14
    ypress
    0.14
     caves
    0.13
    ÑģÑĭ
    0.13
    UIT
    0.13
    Act Density 0.003%

    No Known Activations