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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "reality."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑģÑı
    -0.17
     trÆ°á»Łng
    -0.16
    /fw
    -0.16
    die
    -0.15
    ded
    -0.15
    /share
    -0.14
    ible
    -0.14
    spark
    -0.14
    ican
    -0.14
    manship
    -0.14
    POSITIVE LOGITS
    istically
    0.26
    itious
    0.19
    istic
    0.18
    fully
    0.18
    igned
    0.18
    -world
    0.16
    itous
    0.15
    mente
    0.15
    ually
    0.15
    iad
    0.15
    Act Density 0.025%

    No Known Activations