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

    Neuronpedia

    INDEX
    Explanations

    dates and technical details expressed with numbers

    oai_token-act-pair · gpt-3.5-turbo

    structured data elements, particularly related to people, dates, and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.71
    )."
    -0.70
    .'"
    -0.62
     whichever
    -0.60
    .""
    -0.58
    .).
    -0.58
     dilig
    -0.57
     contamin
    -0.56
     multiplying
    -0.56
     undermin
    -0.55
    POSITIVE LOGITS
    ":{"
    0.80
    ¶
    0.76
     âĵĺ
    0.75
    ®
    0.72
     Miscellaneous
    0.65
    advertising
    0.63
    Buyable
    0.62
     Cosponsors
    0.62
    ELL
    0.61
     Ember
    0.61
    Act Density 0.377%

    No Known Activations