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

    Neuronpedia

    INDEX
    Explanations

    references to time-related phrases focusing on the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically the word "past" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lees
    -0.87
    ivo
    -0.75
    hyde
    -0.71
    ucker
    -0.68
    inventoryQuantity
    -0.65
    tails
    -0.59
    ioned
    -0.59
    âĶ
    -0.58
    ffield
    -0.58
    ================================================================
    -0.58
    POSITIVE LOGITS
     decade
    1.56
     few
    1.47
     couple
    1.42
     fortnight
    1.29
     several
    1.20
     dozen
    1.16
     year
    1.15
     month
    1.14
     fifteen
    1.13
     week
    1.12
    Act Density 0.062%

    No Known Activations