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

    Neuronpedia

    INDEX
    Explanations

    words related to objects and their descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estar
    -0.16
    ëĮĢíĸī
    -0.15
    ÑĪов
    -0.15
    aurus
    -0.15
    оÑģÑĤи
    -0.14
    íĴį
    -0.14
     ober
    -0.14
    exterity
    -0.14
    ãģ£ãģ±
    -0.13
    iola
    -0.13
    POSITIVE LOGITS
    wich
    0.17
     Wid
    0.17
     bach
    0.15
    วà¸ģ
    0.15
    eding
    0.14
    atest
    0.14
    alian
    0.14
    inery
    0.14
    egie
    0.14
    chai
    0.13
    Act Density 0.493%

    No Known Activations