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

    Neuronpedia

    INDEX
    Explanations

    references to popular media and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     konkrét
    -0.08
     doz
    -0.07
    ãĥ¯ãĤ¤ãĥĪ
    -0.07
    onder
    -0.07
    ILT
    -0.07
    ãģŀ
    -0.06
    uyo
    -0.06
    zeug
    -0.06
    à¹Ģà¸Ĺ
    -0.06
    elas
    -0.06
    POSITIVE LOGITS
     America
    0.07
     Dans
    0.06
    Smarty
    0.06
     dance
    0.06
    bis
    0.06
    ObjectContext
    0.06
    λί
    0.06
    以为
    0.06
    Austin
    0.06
     Pru
    0.06
    Act Density 0.002%

    No Known Activations