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

    Neuronpedia

    INDEX
    Explanations

    events or situations that occurred in the recent past

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly those denoted by the word "past" alongside specific durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansk
    -0.79
    cloth
    -0.68
    cius
    -0.65
    VALUE
    -0.62
    olor
    -0.62
    Books
    -0.59
    sers
    -0.59
     stares
    -0.59
    still
    -0.58
    cks
    -0.57
    POSITIVE LOGITS
    ebin
    1.46
     weekend
    1.45
     week
    1.31
     month
    1.14
     year
    1.04
     summer
    1.02
     winter
    1.02
     offseason
    1.01
     decade
    1.01
     WEEK
    1.00
    Act Density 0.029%

    No Known Activations