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

    Neuronpedia

    INDEX
    Explanations

    references to "theory" or discussions about theoretical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.18
    itude
    -0.18
    stones
    -0.18
    ned
    -0.18
    engers
    -0.16
    że
    -0.16
    nem
    -0.15
    ibly
    -0.15
    né
    -0.15
    XS
    -0.15
    POSITIVE LOGITS
    /do
    0.18
    /pr
    0.17
    /the
    0.17
    سÛĮÙĨ
    0.16
    569
    0.16
    OfWork
    0.16
    ical
    0.16
     پرداز
    0.16
    779
    0.16
    czy
    0.16
    Act Density 0.033%

    No Known Activations