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

    Neuronpedia

    INDEX
    Explanations

    words indicating importance and significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¤
    -0.15
    _skin
    -0.15
    ãĥIJãĤ¤
    -0.15
    ses
    -0.15
     pars
    -0.14
    alles
    -0.14
     sÆ°
    -0.13
    lein
    -0.13
    iya
    -0.13
    ìĦ¤
    -0.13
    POSITIVE LOGITS
    _pdata
    0.15
     among
    0.15
    imir
    0.15
    ãĥªãĥ¼ãĤº
    0.14
    -component
    0.14
    iteli
    0.14
    imetype
    0.14
    ottom
    0.14
    à¸ģà¸ķ
    0.14
     item
    0.14
    Act Density 0.096%

    No Known Activations