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

    Neuronpedia

    INDEX
    Explanations

    mentions of fairness, clarity, and simplicity in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating fairness, clarity, or simplicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    melada
    -0.31
    istoitu
    -0.29
     lèvres
    -0.29
     camioneta
    -0.29
    //#
    -0.29
     pelajaran
    -0.28
    //"
    -0.28
    enseits
    -0.28
     Lingkungan
    -0.28
    }//
    -0.28
    POSITIVE LOGITS
     EconPapers
    0.82
    Попис
    0.68
    ValueStyle
    0.65
    MemoryWarning
    0.63
    Respectfully
    0.63
    :✨
    0.61
    WebElementEntity
    0.60
    RegressionTest
    0.59
    LabelTagHelper
    0.58
    GEBURTSDATUM
    0.58
    Act Density 0.028%

    No Known Activations