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

    Neuronpedia

    INDEX
    Explanations

    timestamps indicating the passage of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PR
    -0.62
    enter
    -0.59
    éĹĺ
    -0.59
     Intelligent
    -0.58
     Third
    -0.57
    lite
    -0.57
    rouse
    -0.56
    asio
    -0.55
    lake
    -0.55
    article
    -0.54
    POSITIVE LOGITS
     awhile
    1.35
     years
    1.04
     decades
    1.01
     months
    0.99
     raining
    0.98
     YEAR
    0.97
     centuries
    0.88
     speculated
    0.87
    years
    0.87
     downhill
    0.86
    Act Density 0.057%

    No Known Activations