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

    Neuronpedia

    INDEX
    Explanations

    references to the word "whose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ål
    -0.16
    inta
    -0.15
    ä¸ĸ
    -0.15
    stin
    -0.14
    ys
    -0.14
    ken
    -0.14
    indow
    -0.14
    oman
    -0.13
    ibur
    -0.13
     workbook
    -0.13
    POSITIVE LOGITS
     hod
    0.17
    upon
    0.15
    ungan
    0.15
    ipers
    0.14
    ĽĦ
    0.14
    -www
    0.14
    rieve
    0.13
    วà¸ģ
    0.13
    untu
    0.13
    liš
    0.13
    Act Density 0.011%

    No Known Activations