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

    Neuronpedia

    INDEX
    Explanations

    words related to scheduling and planning, particularly related to events or tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to calendars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.88
    ARP
    -0.87
    ACTED
    -0.75
    Reviewer
    -0.75
    por
    -0.73
    esty
    -0.72
    Priv
    -0.71
    private
    -0.70
    olulu
    -0.70
    upon
    -0.70
    POSITIVE LOGITS
     calendar
    1.43
     calendars
    1.30
     Calendar
    1.19
    endars
    0.84
    endar
    0.75
     schedules
    0.75
     schedule
    0.74
    dule
    0.73
    book
    0.73
     cal
    0.72
    Act Density 0.006%

    No Known Activations