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

    Neuronpedia

    INDEX
    Explanations

    references to institutions and people involved in development or training programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.15
    iffe
    -0.15
    tach
    -0.14
    ocha
    -0.14
    anch
    -0.14
    Detach
    -0.13
     DISCLAIM
    -0.13
    orf
    -0.13
    istrovstvÃŃ
    -0.13
    thur
    -0.13
    POSITIVE LOGITS
    EventListener
    0.17
    IRO
    0.16
    ιÏİ
    0.15
    à¸Ļำ
    0.15
     обла
    0.14
    radu
    0.14
    vla
    0.14
    quila
    0.14
    aeda
    0.14
    lyph
    0.14
    Act Density 0.554%

    No Known Activations