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

    Neuronpedia

    INDEX
    Explanations

    the word "Gener" with varying suffixes and prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "generation" or generational topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.82
    mare
    -0.72
    laus
    -0.69
     McKay
    -0.66
     Sandwich
    -0.63
    ded
    -0.62
    wal
    -0.62
     Sands
    -0.62
    foot
    -0.60
    uku
    -0.60
    POSITIVE LOGITS
    ational
    1.29
    icity
    1.25
    ators
    1.16
    ative
    1.15
    ator
    1.09
    osity
    1.08
    andom
    0.98
    ations
    0.96
    andum
    0.95
    ating
    0.94
    Act Density 0.017%

    No Known Activations