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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a text or article

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     embodi
    -1.05
     depic
    -0.90
     compen
    -0.88
     maneu
    -0.87
     emphat
    -0.87
     unve
    -0.86
     berea
    -0.85
     uniqu
    -0.85
     fischer
    -0.84
     Kün
    -0.84
    POSITIVE LOGITS
    <bos>
    0.68
    IsContent
    0.66
    DoubleQuotes
    0.63
    WriteTagHelper
    0.61
    isContained
    0.61
    ConstraintMaker
    0.59
    ContentAsync
    0.59
     ModelExpression
    0.58
    IsMutable
    0.58
     ویکی‌پدی
    0.57
    Act Density 0.444%

    No Known Activations