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

    Neuronpedia

    INDEX
    Explanations

    references to clickable links or sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibe
    -0.16
    owi
    -0.16
    unner
    -0.15
    以æĿ¥
    -0.15
    _ast
    -0.15
    ellation
    -0.14
    aea
    -0.14
    chat
    -0.14
    chet
    -0.14
    usercontent
    -0.14
    POSITIVE LOGITS
     Merkel
    0.15
    Slinky
    0.15
    acula
    0.14
    .ta
    0.14
    ä¹İ
    0.14
    MPI
    0.13
    αλ
    0.13
    USR
    0.13
    LEV
    0.13
    ÏĢη
    0.13
    Act Density 0.025%

    No Known Activations