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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to colors and vibrant visuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     White
    -0.61
     white
    -0.59
    White
    -0.59
    white
    -0.57
     lime
    -0.56
    ホワイト
    -0.56
     Whites
    -0.55
     whitelist
    -0.55
    Lemon
    -0.54
     Blanc
    -0.54
    POSITIVE LOGITS
     dark
    0.75
     ruby
    0.71
     deep
    0.71
     garnet
    0.71
     maroon
    0.70
     mahogany
    0.65
     burgundy
    0.65
     crimson
    0.63
     donker
    0.62
    dark
    0.62
    Act Density 0.263%

    No Known Activations