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

    Neuronpedia

    INDEX
    Explanations

    references to colors and color-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.76
    iazep
    -0.71
    legate
    -0.69
    QB
    -0.67
    raltar
    -0.67
    ository
    -0.67
    unker
    -0.66
    igun
    -0.65
    llah
    -0.65
    ERN
    -0.63
    POSITIVE LOGITS
     colors
    1.39
     colours
    1.34
     palette
    1.24
     color
    1.23
     tint
    1.21
     brighter
    1.18
     colour
    1.16
     violet
    1.16
     Colors
    1.13
     shades
    1.10
    Act Density 1.557%

    No Known Activations