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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotation marks and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.77
     itſelf
    -0.73
    ſelf
    -0.72
     themſelves
    -0.72
     houſe
    -0.68
     Houſe
    -0.68
     Jefus
    -0.67
     Shaksp
    -0.65
     Diſ
    -0.64
     againſt
    -0.63
    POSITIVE LOGITS
    GraphicsUnit
    0.64
    SourceChecksum
    0.63
     AssemblyCulture
    0.58
    mergeFrom
    0.55
    PhysRevD
    0.54
    DoubleQuotes
    0.54
    onViewCreated
    0.51
    UnsafeEnabled
    0.50
    Referències
    0.50
    例文帳に追加
    0.50
    Act Density 0.217%

    No Known Activations