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

    Neuronpedia

    INDEX
    Explanations

    references to the word "paint" at varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to paint and painting-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     htt
    -0.80
    doms
    -0.78
    indal
    -0.75
    zbek
    -0.73
     Kenyan
    -0.69
    atches
    -0.67
    AMY
    -0.66
    cgi
    -0.65
    otide
    -0.65
    scill
    -0.64
    POSITIVE LOGITS
    brush
    1.25
     thinner
    0.94
    balls
    0.89
    ball
    0.85
    isans
    0.84
     brushes
    0.83
    pain
    0.83
     painter
    0.81
     acrylic
    0.81
     painting
    0.80
    Act Density 0.049%

    No Known Activations