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

    Neuronpedia

    INDEX
    Explanations

    dates and times of publication in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Published" followed by a date or timestamp

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     camp
    -0.73
     stra
    -0.70
     tier
    -0.66
     around
    -0.64
     stats
    -0.64
     halls
    -0.63
     shower
    -0.63
     mid
    -0.62
     hall
    -0.61
     armor
    -0.61
    POSITIVE LOGITS
    Published
    4.79
     Published
    1.72
    published
    1.43
    Reviewed
    1.39
    Posted
    1.33
    Released
    1.23
    Publisher
    1.23
    Written
    1.17
    Author
    1.12
    Interstitial
    1.04
    Act Density 0.013%

    No Known Activations