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

    Neuronpedia

    INDEX
    Explanations

    color-related terms

    oai_token-act-pair · gpt-3.5-turbo

    color descriptors and representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -1.00
    uthor
    -0.81
    olicy
    -0.80
    _-
    -0.79
    idem
    -0.75
    cffffcc
    -0.68
    llah
    -0.68
    ernel
    -0.64
     Farage
    -0.64
    =-=-
    -0.63
    POSITIVE LOGITS
    blind
    1.20
     palette
    1.09
    ="#
    0.93
    anguage
    0.93
     coded
    0.89
    ado
    0.87
     dye
    0.85
    way
    0.85
     tint
    0.84
    imeter
    0.83
    Act Density 0.056%

    No Known Activations