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

    Neuronpedia

    INDEX
    Explanations

    references to human nature and moral depravity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    लब
    -0.18
    .updateDynamic
    -0.17
    ptime
    -0.17
    cheon
    -0.17
    nze
    -0.16
    istrovstvÃŃ
    -0.16
    bla
    -0.16
    \brief
    -0.16
    _PT
    -0.15
    ukan
    -0.15
    POSITIVE LOGITS
     fallen
    0.20
     Adam
    0.19
     since
    0.18
     Fallen
    0.18
     nature
    0.18
    0.18
     corruption
    0.17
     Seed
    0.17
     ven
    0.17
     fell
    0.16
    Act Density 0.046%

    No Known Activations