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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific items being painted, such as objects and buildings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTAL
    -0.79
    raltar
    -0.75
    sie
    -0.75
    unker
    -0.73
     Carnegie
    -0.71
    ancock
    -0.67
     drill
    -0.67
    nesota
    -0.66
    doms
    -0.66
    TAIN
    -0.65
    POSITIVE LOGITS
     colors
    1.16
     colours
    1.13
     tint
    1.09
     decoration
    1.04
     color
    1.04
     colour
    1.03
     painter
    1.02
    Color
    1.01
     portraits
    0.99
     silhou
    0.99
    Act Density 5.019%

    No Known Activations