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

    Neuronpedia

    INDEX
    Explanations

    references to religious authority and teachings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’”
    -0.52
    parsedMessage
    -0.50
    ”
    -0.49
     wewnętr
    -0.49
    onomía
    -0.47
    ”?
    -0.47
    irvana
    -0.47
    ”—
    -0.46
     clave
    -0.44
    ”:
    -0.44
    POSITIVE LOGITS
     ſte
    0.83
     ſche
    0.81
    EndContext
    0.81
     houſe
    0.77
     myſelf
    0.74
     purpoſe
    0.73
     ſta
    0.73
    LEGGI
    0.72
     ſeveral
    0.72
     ſch
    0.70
    Act Density 1.178%

    No Known Activations