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

    Neuronpedia

    INDEX
    Explanations

    colors mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    lists of colors or color combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BIL
    -0.80
    cffff
    -0.72
    hran
    -0.72
     Mub
    -0.70
    taker
    -0.69
    izarre
    -0.69
     Ethics
    -0.68
    atican
    -0.68
     Clinic
    -0.67
    ariat
    -0.67
    POSITIVE LOGITS
    medium
    0.82
     arrow
    0.80
    cloth
    0.79
    oxide
    0.78
     striped
    0.77
    skinned
    0.75
     blot
    0.74
    haired
    0.73
    chrom
    0.71
     stain
    0.70
    Act Density 0.404%

    No Known Activations