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

    Neuronpedia

    INDEX
    Explanations

    concepts related to morality and spiritual beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =?",
    -0.17
    ï¼īãģ¯
    -0.17
    CLS
    -0.16
    .`,↵
    -0.16
    ãĢij,
    -0.16
    abbix
    -0.16
    ï¼ī:
    -0.15
     =",
    -0.15
    \',
    -0.15
     "...
    -0.15
    POSITIVE LOGITS
    ”
    0.40
    "(
    0.37
    "
    0.37
    »
    0.35
    )
    0.32
    \)
    0.30
     '(
    0.29
    )(
    0.28
    ")(
    0.28
    “(
    0.28
    Act Density 0.091%

    No Known Activations