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

    Neuronpedia

    INDEX
    Explanations

    programming-related data types and method signatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CAA
    -0.15
    apro
    -0.15
    odos
    -0.15
    æĿIJæĸĻ
    -0.15
    indre
    -0.15
    .realm
    -0.14
    ảo
    -0.14
    oko
    -0.14
     ruk
    -0.14
    Workbook
    -0.14
    POSITIVE LOGITS
     âĹĦ
    0.17
    fm
    0.16
    quared
    0.14
    <>
    0.14
     Nab
    0.14
    fade
    0.14
    acker
    0.14
    ared
    0.14
    /her
    0.14
    adier
    0.14
    Act Density 0.007%

    No Known Activations