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

    Neuronpedia

    INDEX
    Explanations

    specific characters such as accents and special symbols

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and apostrophes, indicating dialogue or contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.78
    è¦ļéĨĴ
    -0.75
    ategory
    -0.71
    yip
    -0.69
    Buyable
    -0.69
    ensional
    -0.67
    odium
    -0.66
    imo
    -0.66
    assetsadobe
    -0.66
    ratulations
    -0.65
    POSITIVE LOGITS
    s
    0.87
    ll
    0.85
    ÃŃs
    0.78
    ards
    0.73
    £
    0.71
    ghan
    0.69
    ¼
    0.68
    Ī
    0.68
    \'
    0.68
    ĩ
    0.68
    Act Density 0.232%

    No Known Activations