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

    Neuronpedia

    INDEX
    Explanations

    text formatting related elements such as specific characters, numbers, and symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to measurements or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.72
     hiber
    -0.71
     tremend
    -0.70
    tsky
    -0.70
    hement
    -0.70
    atis
    -0.69
    ennes
    -0.67
     undermin
    -0.64
    stra
    -0.62
    ucci
    -0.61
    POSITIVE LOGITS
    ³³³
    0.92
    ³³³³
    0.83
    ³³³³³³³³
    0.77
    ³³³³³³³³³³³³³³³³
    0.75
    Catalog
    0.69
    Avg
    0.69
     Frequency
    0.68
     |--
    0.65
    ·
    0.65
    ³³
    0.64
    Act Density 0.216%

    No Known Activations