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

    Neuronpedia

    INDEX
    Explanations

    references to records or notable achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isan
    -0.17
    endor
    -0.16
    imoto
    -0.16
    izzato
    -0.15
    itzer
    -0.15
    840
    -0.15
    apon
    -0.15
    921
    -0.15
    iso
    -0.14
    tridge
    -0.14
    POSITIVE LOGITS
    -breaking
    0.31
    keeping
    0.29
    -setting
    0.24
    breaking
    0.23
    ings
    0.23
    ant
    0.19
     breaking
    0.19
    keeper
    0.19
    breaker
    0.19
     setters
    0.18
    Act Density 0.028%

    No Known Activations