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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kur
    -0.17
    æĿ¥èĩª
    -0.16
    rap
    -0.16
    оба
    -0.15
    elsen
    -0.15
    rape
    -0.14
    ussen
    -0.14
    ekim
    -0.14
    /linux
    -0.14
    loat
    -0.14
    POSITIVE LOGITS
    raquo
    0.15
     fray
    0.15
     beyond
    0.15
    632
    0.15
    åŁ
    0.14
    ÙĪÙī
    0.14
    ellig
    0.14
    ê¸ī
    0.14
    ional
    0.13
    utting
    0.13
    Act Density 0.088%

    No Known Activations