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

    Neuronpedia

    INDEX
    Explanations

    statements concerning an event or a report made by authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antis
    -0.16
    à¸Ľà¸£à¸°à¸Īำ
    -0.15
     antis
    -0.15
     shadow
    -0.15
    ög
    -0.14
     unp
    -0.14
    impl
    -0.14
     Tel
    -0.14
    SPA
    -0.14
     Nisan
    -0.14
    POSITIVE LOGITS
    ayet
    0.16
    kaar
    0.15
    Leaks
    0.15
    anine
    0.15
    cellent
    0.14
    lech
    0.14
    /il
    0.14
    etim
    0.13
    rente
    0.13
    ilate
    0.13
    Act Density 0.154%

    No Known Activations