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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating societal norms and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.68
     فريبيس
    -0.65
     виправивши
    -0.61
    WindowConstants
    -0.59
    ChildScrollView
    -0.58
    fflush
    -0.57
    DockStyle
    -0.56
    ########.
    -0.55
    testify
    -0.55
     تضيفلها
    -0.55
    POSITIVE LOGITS
     considered
    1.95
     viewed
    1.93
     regarded
    1.90
    considered
    1.60
     view
    1.58
     perceived
    1.58
     Considered
    1.54
     seen
    1.52
     deemed
    1.50
     considéré
    1.43
    Act Density 0.703%

    No Known Activations