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

    Neuronpedia

    INDEX
    Explanations

    elements related to documentation or configuration files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.79
    Bronnen
    -0.68
    之色
    -0.65
    DOCTYPE
    -0.64
     تعدى
    -0.64
    TabStop
    -0.63
    esterday
    -0.62
    ;
    -0.62
    IntoConstraints
    -0.62
    Бахар
    -0.61
    POSITIVE LOGITS
    ✨
    2.20
     ✨
    1.60
    :✨
    1.56
    ✨✨
    1.25
    ✨:
    1.24
    ⭐️
    0.92
    💕
    0.89
    ❤️
    0.87
    🌟
    0.85
    💫
    0.81
    Act Density 0.034%

    No Known Activations