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

    Neuronpedia

    INDEX
    Explanations

    the word "zh" occurring with different numeric values

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, specifically related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adian
    -0.77
    ples
    -0.70
    tailed
    -0.65
     Lowry
    -0.64
     Tempest
    -0.64
    houses
    -0.62
     propriet
    -0.62
     Pear
    -0.62
    holders
    -0.61
     denomin
    -0.61
    POSITIVE LOGITS
    acket
    1.04
    externalActionCode
    0.90
    wcsstore
    0.90
    zh
    0.87
    enegger
    0.85
    -|
    0.83
    ा
    0.80
    ÑĮ
    0.79
    usercontent
    0.78
    apeake
    0.78
    Act Density 0.019%

    No Known Activations