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

    Neuronpedia

    INDEX
    Explanations

    dates and time periods

    oai_token-act-pair · gpt-3.5-turbo

    temporal indicators, specifically references to early and late time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.75
    icion
    -0.71
    oppable
    -0.69
    hyde
    -0.68
    inguished
    -0.64
    irs
    -0.62
    oldown
    -0.62
    agonist
    -0.62
    itutional
    -0.61
     Rebell
    -0.61
    POSITIVE LOGITS
     June
    1.33
     February
    1.32
     April
    1.31
     October
    1.29
     August
    1.29
     July
    1.28
     December
    1.28
     January
    1.27
     November
    1.26
     September
    1.24
    Act Density 0.035%

    No Known Activations