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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    featureID
    -0.88
     AssemblyCulture
    -0.87
    ThroughAttribute
    -0.85
    InvalidProtocol
    -0.76
    setupUi
    -0.71
    /*---
    -0.69
    MemoryWarning
    -0.68
    webElementXpaths
    -0.68
     AssemblyTitle
    -0.67
     ویکی‌پدی
    -0.67
    POSITIVE LOGITS
     permis
    0.59
    ilis
    0.57
    strument
    0.56
     Shining
    0.56
    ặc
    0.55
    τογραφ
    0.53
    licant
    0.52
    VIRONMENT
    0.52
    gänge
    0.52
    ÍC
    0.52
    Act Density 0.000%

    No Known Activations