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

    Neuronpedia

    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related phrases, specifically occurrences of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.72
    oller
    -0.62
    icons
    -0.61
    lessness
    -0.61
    Null
    -0.61
    rored
    -0.60
    facts
    -0.59
    rikes
    -0.59
    rics
    -0.58
    warts
    -0.57
    POSITIVE LOGITS
     weekend
    1.34
     week
    1.30
     month
    1.21
     summer
    1.20
     autumn
    1.18
     afternoon
    1.18
     upcoming
    1.18
     year
    1.17
     evening
    1.12
     winter
    1.08
    Act Density 0.057%

    No Known Activations