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

    Neuronpedia

    INDEX
    Explanations

    phrases related to timeframes and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decades
    -0.28
     centuries
    -0.21
     decade
    -0.18
     century
    -0.18
    ernet
    -0.18
    lue
    -0.18
     Five
    -0.17
     millennia
    -0.17
     Ten
    -0.16
    strup
    -0.16
    POSITIVE LOGITS
     year
    0.39
     Year
    0.34
     YEAR
    0.31
    Year
    0.31
    year
    0.31
    -year
    0.28
    YEAR
    0.27
    ä¸Ģå¹´
    0.27
     jaar
    0.26
     año
    0.26
    Act Density 0.141%

    No Known Activations