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

    Neuronpedia

    INDEX
    Explanations

    terms related to navigation, data, and media availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnderTest
    -0.15
    _ls
    -0.15
    unta
    -0.15
    lesi
    -0.14
    _TYP
    -0.14
     Helmet
    -0.14
    unders
    -0.14
    ÑģÑİ
    -0.14
    ilton
    -0.14
    weet
    -0.14
    POSITIVE LOGITS
    rup
    0.17
    оза
    0.16
    strain
    0.15
    /full
    0.15
    Ñĥла
    0.15
     ench
    0.14
    emd
    0.14
    azzo
    0.14
    hare
    0.14
    udu
    0.14
    Act Density 0.065%

    No Known Activations