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

    Neuronpedia

    INDEX
    Explanations

    references to events or occurrences happening over the past year

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time, specifically focusing on the term "year."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Facilities
    -0.73
     Hearts
    -0.62
     Andromeda
    -0.62
     Clause
    -0.61
     thumbs
    -0.60
     Controls
    -0.60
     Selection
    -0.59
     Else
    -0.59
     Desk
    -0.57
     blue
    -0.57
    POSITIVE LOGITS
    long
    0.95
    orate
    0.88
    frames
    0.86
    days
    0.86
    ruary
    0.83
    dozen
    0.79
    asons
    0.78
    lot
    0.75
    nard
    0.75
    los
    0.74
    Act Density 0.069%

    No Known Activations