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

    Neuronpedia

    INDEX
    Explanations

    news articles mentioning the age of individuals involved in incidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ages in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.60
     conventions
    -0.58
    ovie
    -0.55
     Closing
    -0.54
     clos
    -0.53
     Strongh
    -0.53
     endorsements
    -0.53
    £ı
    -0.53
     Destination
    -0.53
    lections
    -0.53
    POSITIVE LOGITS
    -
    1.07
    yr
    1.05
    yrs
    0.94
    year
    0.92
    -[
    0.91
    th
    0.91
     yr
    0.89
    yo
    0.89
     year
    0.83
    acious
    0.82
    Act Density 0.078%

    No Known Activations