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

    Neuronpedia

    INDEX
    Explanations

    references to technology product series

    oai_token-act-pair · gpt-3.5-turbo

    mentions of product series or model numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bled
    -0.84
    bered
    -0.75
    arching
    -0.74
    selves
    -0.74
    adel
    -0.72
    bats
    -0.71
    rette
    -0.69
    prus
    -0.69
    bling
    -0.69
    inently
    -0.67
    POSITIVE LOGITS
    CI
    0.81
    manship
    0.75
    GP
    0.75
    ctive
    0.75
    ĸļ
    0.74
    BuyableInstoreAndOnline
    0.74
    Series
    0.71
    CRIP
    0.70
    Graph
    0.69
    andi
    0.69
    Act Density 0.028%

    No Known Activations