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

    Neuronpedia

    INDEX
    Explanations

    informational phrases or buzzwords related to the topic being discussed

    oai_token-act-pair · gpt-3.5-turbo

    informative content aimed at providing guidance or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    netflix
    -0.66
    ibu
    -0.64
    æ©
    -0.62
    groupon
    -0.61
     Reincarnated
    -0.60
    cult
    -0.59
    ahu
    -0.59
     Demand
    -0.59
    ItemTracker
    -0.58
     chau
    -0.58
    POSITIVE LOGITS
     spoiler
    1.01
     spoilers
    0.95
     ital
    0.95
    OIL
    0.94
     disclaimer
    0.91
     suffice
    0.91
     caveats
    0.90
     please
    0.90
     gist
    0.90
     chronological
    0.90
    Act Density 0.770%

    No Known Activations