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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate cause and effect relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkel
    -0.15
    ICAST
    -0.15
    osl
    -0.15
    аÑĢам
    -0.15
    amente
    -0.15
    ctal
    -0.14
    ļĮ
    -0.14
    ild
    -0.14
    chk
    -0.13
    bas
    -0.13
    POSITIVE LOGITS
    uard
    0.18
    geries
    0.18
    aland
    0.16
    mlin
    0.15
     example
    0.15
    -profit
    0.15
     instance
    0.14
    Ùĩر
    0.14
    arth
    0.14
     permission
    0.14
    Act Density 0.004%

    No Known Activations