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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific phrases that indicate decision-making or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.73
    XmlAccessType
    -0.68
    RectangleBorder
    -0.67
     saites
    -0.67
    __);
    -0.61
     StatefulWidget
    -0.61
    StoryboardSegue
    -0.59
    $.
    -0.58
    '))
    -0.57
    ()]);
    -0.57
    POSITIVE LOGITS
     get
    1.00
     keep
    0.95
     Get
    0.95
     make
    0.95
     Make
    0.89
     take
    0.86
    Get
    0.86
    Make
    0.82
    make
    0.79
     Keep
    0.79
    Act Density 0.342%

    No Known Activations