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

    Neuronpedia

    INDEX
    Explanations

    elements related to assertions and testing in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icy
    -0.16
    ainen
    -0.15
    ny
    -0.15
     unn
    -0.14
     Stuart
    -0.14
    ius
    -0.14
    numbers
    -0.14
     Hers
    -0.14
    rack
    -0.14
    æ°Ĺ
    -0.13
    POSITIVE LOGITS
    Äĥm
    0.17
    ++++++++
    0.16
    ++++++++++++++++
    0.14
    ++++++++++++++++++++++++++++++++
    0.14
    igkeit
    0.14
    keley
    0.14
    _NC
    0.14
    ä¸ĺ
    0.14
     Jacket
    0.14
    xbe
    0.13
    Act Density 0.008%

    No Known Activations