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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific periods of time in relation to changes or trends

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically the phrases "recent years" and "months."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tomorrow
    -0.70
     2021
    -0.67
     2020
    -0.67
     1908
    -0.66
     2022
    -0.65
    ilater
    -0.64
     1901
    -0.63
     1911
    -0.62
    iox
    -0.61
     1902
    -0.61
    POSITIVE LOGITS
    )=(
    0.82
     embold
    0.69
    forward
    0.68
    Reviewer
    0.67
    é¾įåĸļ士
    0.66
     thanks
    0.66
    cape
    0.65
     louder
    0.64
     resur
    0.63
     owing
    0.62
    Act Density 0.093%

    No Known Activations