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

    Neuronpedia

    INDEX
    Explanations

    references to statistical measures, specifically standard deviation and standard error of the mean

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    mands
    -0.62
     gegenüber
    -0.53
     verksam
    -0.51
     dépasse
    -0.51
     gioielli
    -0.51
     lavoratori
    -0.50
    BeginContext
    -0.49
    Praxis
    -0.49
     FormsModule
    -0.48
     للاسماء
    -0.48
    POSITIVE LOGITS
    Autoritní
    0.60
     finite
    0.55
    orianCalendar
    0.54
    intios
    0.53
    GRAV
    0.52
     Faraday
    0.51
    LayoutConstraint
    0.51
     saar
    0.51
     tons
    0.50
    はじめに
    0.50
    Act Density 0.003%

    No Known Activations