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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions related to time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andra
    -0.62
    ãĥĢ
    -0.61
    grave
    -0.59
     Bir
    -0.59
    don
    -0.57
    Exactly
    -0.57
    utters
    -0.57
     stakes
    -0.56
    ahn
    -0.55
     Schwarz
    -0.54
    POSITIVE LOGITS
     ago
    1.05
     elapsed
    0.82
     Ago
    0.80
    hift
    0.76
     mornings
    0.72
     olds
    0.71
     apiece
    0.70
    assetsadobe
    0.70
     evenings
    0.68
     lapse
    0.68
    Act Density 0.115%

    No Known Activations