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

    Neuronpedia

    INDEX
    Explanations

    color-related terms or the word "color"

    oai_token-act-pair · gpt-3.5-turbo

    references to colors or color-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -1.05
    idem
    -0.86
    _-
    -0.85
    olicy
    -0.78
    iddles
    -0.73
    ammad
    -0.73
    OTAL
    -0.72
    uthor
    -0.72
    =-=-=-=-
    -0.71
    Xi
    -0.70
    POSITIVE LOGITS
    blind
    1.05
     palette
    1.01
     coded
    0.86
     color
    0.83
    color
    0.82
    grain
    0.82
    pain
    0.81
     Spray
    0.80
    ="#
    0.79
    fully
    0.79
    Act Density 0.018%

    No Known Activations