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

    Neuronpedia

    INDEX
    Explanations

    references to time and durations related to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.54
    hezza
    -0.45
    ViewFeatures
    -0.43
     Less
    -0.42
    zeichnen
    -0.42
    Brief
    -0.42
    ýchod
    -0.41
     ugy
    -0.41
    zustellen
    -0.40
    guid
    -0.40
    POSITIVE LOGITS
     decades
    1.03
     years
    0.93
    years
    0.88
     YEARS
    0.86
    YEARS
    0.85
     decade
    0.84
     ages
    0.84
     yıllar
    0.81
    Years
    0.81
     centuries
    0.79
    Act Density 0.192%

    No Known Activations