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

    Neuronpedia

    INDEX
    Explanations

    references to leadership and authority figures in various contexts

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

    officials and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.43
    ViewFeatures
    -0.36
     haar
    -0.35
     مظ
    -0.32
    Ран
    -0.32
    还是
    -0.32
     Brand
    -0.31
    laar
    -0.31
     ändå
    -0.31
     yet
    -0.31
    POSITIVE LOGITS
     CURIAM
    0.57
    ChildScrollView
    0.56
    Personendaten
    0.56
    AddHtmlAttribute
    0.53
    AccessorTable
    0.53
    tanleria
    0.49
    Rüyada
    0.49
    oplayer
    0.48
     
    0.48
    itinéraire
    0.48
    Act Density 0.256%

    No Known Activations