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

    Neuronpedia

    INDEX
    Explanations

    specific colors and their properties within text or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whites
    -0.65
    audiovisuel
    -0.63
     criticised
    -0.57
     fertil
    -0.55
    Whites
    -0.55
     White
    -0.55
     Ages
    -0.55
     levelling
    -0.53
    White
    -0.53
     ages
    -0.52
    POSITIVE LOGITS
     color
    2.79
    color
    2.42
     Color
    2.14
     colour
    2.11
    Color
    2.10
     COLOR
    1.94
    COLOR
    1.75
     couleur
    1.66
     colore
    1.60
     kleur
    1.57
    Act Density 0.254%

    No Known Activations