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

    Neuronpedia

    INDEX
    Explanations

    numerical values and specific numeric patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iola
    -0.17
    UDA
    -0.16
    velt
    -0.15
    urette
    -0.15
    ån
    -0.15
     contact
    -0.15
    kker
    -0.15
    è±Ĭ
    -0.14
    baugh
    -0.14
    mpp
    -0.14
    POSITIVE LOGITS
    ernes
    0.15
    thed
    0.15
    amoto
    0.14
    odic
    0.14
    pell
    0.14
    amar
    0.13
     Allan
    0.13
    etime
    0.13
    etch
    0.13
    thetic
    0.13
    Act Density 0.090%

    No Known Activations