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

    Neuronpedia

    INDEX
    Explanations

    dates or references to events

    oai_token-act-pair · gpt-3.5-turbo

    the word "today" and its multiple instances in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.78
    imov
    -0.74
    ippi
    -0.72
    sym
    -0.68
    chest
    -0.68
    med
    -0.68
    alcohol
    -0.67
    hma
    -0.65
    cephal
    -0.65
    cientious
    -0.64
    POSITIVE LOGITS
     afternoon
    1.02
     morning
    0.97
     today
    0.91
     Today
    0.88
    adays
    0.86
    days
    0.83
    today
    0.83
     TODAY
    0.83
     Tonight
    0.82
     mornings
    0.80
    Act Density 0.031%

    No Known Activations