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

    Neuronpedia

    INDEX
    Explanations

    various forms of punctuation or quotation marks used in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    drž
    -0.53
    prav
    -0.53
     scolaires
    -0.52
     prépar
    -0.50
    imental
    -0.49
     médicaux
    -0.47
    minal
    -0.47
    つけた
    -0.47
    Target
    -0.47
    mainPanel
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    1.26
     autorytatywna
    1.25
    aarrggbb
    1.23
    IntoConstraints
    1.16
     disambiguazione
    1.14
    OGND
    1.11
    awtextra
    1.11
     CreateTagHelper
    1.09
     <=",
    1.02
     للمعارف
    1.01
    Act Density 0.024%

    No Known Activations