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

    Neuronpedia

    INDEX
    Explanations

    instances where a specific time period is mentioned, such as "days" or "weeks"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to timeframes and recent occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     someday
    -0.82
     Benefits
    -0.65
     Type
    -0.64
    inav
    -0.62
     ut
    -0.62
     Codes
    -0.62
    reat
    -0.62
    later
    -0.61
    inet
    -0.60
     Sob
    -0.59
    POSITIVE LOGITS
    maxwell
    0.77
    flower
    0.74
    undreds
    0.73
    hift
    0.73
    ı
    0.72
    aptic
    0.71
     afternoon
    0.70
     embold
    0.70
    dozen
    0.70
     uproar
    0.69
    Act Density 0.141%

    No Known Activations