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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and arguments regarding morality and hypocrisy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ution
    -0.14
    utton
    -0.14
    umes
    -0.14
     jin
    -0.13
    arms
    -0.13
    aging
    -0.13
     Kami
    -0.13
    utions
    -0.13
    agi
    -0.13
    pragma
    -0.13
    POSITIVE LOGITS
    ικη
    0.16
    èĶµ
    0.16
    utz
    0.16
    igel
    0.15
    ustos
    0.15
    Âłtom
    0.14
    ลาย
    0.14
    iyim
    0.14
    ewire
    0.14
     ÃĸrneÄŁin
    0.14
    Act Density 0.302%

    No Known Activations