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

    Neuronpedia

    INDEX
    Explanations

    parentheses or brackets in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ārējās
    -0.60
    Clik
    -0.58
    PasswordEncoder
    -0.58
     TestBed
    -0.56
    المل
    -0.56
    mentaux
    -0.56
    tikai
    -0.55
    __*/
    -0.55
    inj
    -0.54
    SceneManagement
    -0.54
    POSITIVE LOGITS
     USP
    2.00
    허
    1.36
    USP
    1.23
    usp
    0.78
    IsContent
    0.70
    原始内容存档于
    0.69
    出版年
    0.65
     autorytatywna
    0.63
    RegressionTest
    0.56
    zbęd
    0.56
    Act Density 0.008%

    No Known Activations