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

    Neuronpedia

    INDEX
    Explanations

    keywords related to media manipulation and political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    شاف
    -0.81
    RectangleBorder
    -0.59
    IsMutable
    -0.57
    BufferException
    -0.56
     reconn
    -0.56
    ophilus
    -0.54
     acrylique
    -0.51
    breakpoints
    -0.51
     debout
    -0.50
    styleable
    -0.50
    POSITIVE LOGITS
     painting
    0.70
     paint
    0.69
     whipped
    0.68
     ped
    0.68
     demon
    0.67
     PAINT
    0.65
     portraying
    0.65
     paints
    0.64
    paint
    0.63
     whipping
    0.63
    Act Density 0.603%

    No Known Activations