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

    Neuronpedia

    INDEX
    Explanations

    terms related to color and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _colors
    -0.25
    Colors
    -0.24
     colourful
    -0.23
    Color
    -0.22
     colorful
    -0.20
     Colors
    -0.20
     colours
    -0.20
    _colour
    -0.19
     Coloring
    -0.19
     coloured
    -0.18
    POSITIVE LOGITS
    ation
    0.36
    -coded
    0.35
    blind
    0.34
     scheme
    0.31
    fully
    0.30
     schemes
    0.30
    atura
    0.28
    ado
    0.28
    way
    0.27
    fast
    0.27
    Act Density 0.056%

    No Known Activations