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

    Neuronpedia

    INDEX
    Explanations

    words related to visual elements, such as visualization, visual effects, and representation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visual representation and visualization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.85
    shire
    -0.84
    unin
    -0.80
    olicy
    -0.79
    kson
    -0.79
    qv
    -0.77
     Carnegie
    -0.76
    enne
    -0.75
    lot
    -0.70
    uddin
    -0.68
    POSITIVE LOGITS
    izations
    1.35
    isations
    1.31
    isation
    1.19
    izable
    1.18
    izing
    1.16
    ized
    1.13
    izer
    1.12
    izers
    1.09
    izes
    1.08
    ization
    1.05
    Act Density 0.032%

    No Known Activations