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

    Neuronpedia

    INDEX
    Explanations

    descriptors and characteristics of colors and shades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynes
    -0.18
     colorful
    -0.17
    kea
    -0.16
     Ple
    -0.16
    erap
    -0.15
     colourful
    -0.15
    purple
    -0.15
    morgan
    -0.15
     vis
    -0.14
    ihn
    -0.14
    POSITIVE LOGITS
     deep
    0.21
     Deep
    0.19
    ãĥ³ãĤ°ãĥ«
    0.19
    Deep
    0.18
     slate
    0.17
    deep
    0.17
     kh
    0.16
     deepest
    0.15
    utter
    0.15
    linger
    0.15
    Act Density 0.081%

    No Known Activations