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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific actions or notable events in a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     bourg
    -0.76
     Shakspeare
    -0.76
     Whence
    -0.74
     noyau
    -0.74
     carrefour
    -0.73
     ekos
    -0.71
     delà
    -0.68
     xxvi
    -0.67
     Chapitre
    -0.67
     kooper
    -0.66
    POSITIVE LOGITS
     paragraph
    0.71
     section
    0.70
     listing
    0.70
     listed
    0.66
     mention
    0.66
     mentions
    0.62
     page
    0.61
     paragraphs
    0.61
     description
    0.58
     wording
    0.57
    Act Density 0.661%

    No Known Activations