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

    Neuronpedia

    INDEX
    Explanations

    significant mentions of time-related events.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of personal events and experiences.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to "yesterday" or recent past events, often activating strongly on the word "yesterday" and nearby words indicating the passage of time.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    days (yesterday, today, night)

    np_acts-logits-general · gemini-2.0-flash

    yesterday and recent past

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.60
    ormais
    -0.54
    neurial
    -0.53
    sproz
    -0.52
    ="">
    -0.51
     Ferris
    -0.50
    =").
    -0.49
    intérêt
    -0.49
     suivantes
    -0.48
     diabe
    -0.48
    POSITIVE LOGITS
    esterday
    0.76
     виправивши
    0.73
    terday
    0.71
     today
    0.70
    ORROW
    0.68
    yesterday
    0.66
    WebVitals
    0.65
     дописавши
    0.65
     yesterday
    0.64
     Paglinawan
    0.62
    Act Density 0.054%

    No Known Activations