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

    Neuronpedia

    INDEX
    Explanations

    descriptions of products and their various characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to varieties and types of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culosis
    -0.75
    notice
    -0.74
    iron
    -0.73
    ItemTracker
    -0.69
    Failure
    -0.69
    icans
    -0.67
    exit
    -0.67
     vigilant
    -0.66
    reon
    -0.66
    Luke
    -0.65
    POSITIVE LOGITS
     styles
    1.56
     varieties
    1.51
     sizes
    1.44
     variety
    1.43
     colors
    1.42
     colours
    1.42
     flavors
    1.41
     genres
    1.39
     flavours
    1.39
     combinations
    1.38
    Act Density 0.472%

    No Known Activations