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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related terms, like "Today" and "century"

    oai_token-act-pair · gpt-3.5-turbo

    references to the present time or contemporary issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashes
    -0.65
     priority
    -0.63
    \":
    -0.62
     Hits
    -0.60
     apprehens
    -0.59
    ashing
    -0.59
     coordinating
    -0.57
    "},"
    -0.57
     splash
    -0.57
     Intake
    -0.57
    POSITIVE LOGITS
    remember
    0.78
    yond
    0.75
     remember
    0.74
     hindsight
    0.71
    ury
    0.71
     recalled
    0.71
    Fast
    0.68
     ital
    0.68
     remembered
    0.68
     recalls
    0.67
    Act Density 0.610%

    No Known Activations