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

    Neuronpedia

    INDEX
    Explanations

    specific numeric and alphanumeric patterns within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _TRACE
    -0.16
    deen
    -0.16
    ricks
    -0.15
    ÏĦή
    -0.15
    heimer
    -0.14
    ед
    -0.14
    ClientRect
    -0.14
    pst
    -0.14
    pj
    -0.14
    ÑģиÑı
    -0.14
    POSITIVE LOGITS
    fold
    0.18
    ième
    0.17
    .appspot
    0.17
    th
    0.16
    -fold
    0.15
    /th
    0.14
    deg
    0.14
    -th
    0.14
    son
    0.14
    nger
    0.14
    Act Density 0.093%

    No Known Activations