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

    Neuronpedia

    INDEX
    Explanations

    the word "paint" with varying degrees of significance or contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of paint in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zbek
    -0.83
    nesses
    -0.81
    AMY
    -0.81
    doms
    -0.75
    ITED
    -0.73
    atches
    -0.73
    cgi
    -0.73
    scill
    -0.72
     htt
    -0.72
    -|
    -0.70
    POSITIVE LOGITS
    brush
    1.15
     thinner
    1.05
     paints
    0.92
     paint
    0.89
     painted
    0.89
     painter
    0.88
     painting
    0.87
     Painter
    0.84
     acrylic
    0.82
    wright
    0.80
    Act Density 0.021%

    No Known Activations