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

    Neuronpedia

    INDEX
    Explanations

    quotation marks or dialogue indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.57
    I
    -0.32
    sar
    -0.26
    sburg
    -0.24
    ä½Ĩ
    -0.24
    Ùĩ
    -0.24
    æѤ
    -0.23
    ska
    -0.23
    a
    -0.23
    sik
    -0.23
    POSITIVE LOGITS
    Ve
    0.18
    gether
    0.16
    .sz
    0.15
    urent
    0.14
    /'
    0.14
    urai
    0.14
    ainen
    0.14
    readcr
    0.14
    odont
    0.14
    porno
    0.13
    Act Density 0.051%

    No Known Activations