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

    Neuronpedia

    INDEX
    Explanations

    time periods expressed in days, months, or years.

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

    specific timeframes or durations, particularly in terms of days, weeks, months, or years.

    oai_token-act-pair · gpt-4oTriggered by @jbloomaus

    time intervals.

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

    temporal references such as days, weeks, months, or years

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

    Units of time (days, years, months)

    np_acts-logits-general · gemini-2.0-flash

    time durations

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases expressing specific time durations or periods (like "three days," "two weeks," "five years," etc.).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @kparkhamchuk
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.59
    Obrázky
    -0.59
    setViewportView
    -0.58
    mybatisplus
    -0.58
     DialogInterface
    -0.51
    charCodeAt
    -0.50
    Personendaten
    -0.46
    cloudflare
    -0.46
     ويكيميديا
    -0.44
    loài
    -0.44
    POSITIVE LOGITS
     time
    1.03
     flat
    0.96
     tijd
    0.87
    time
    0.85
    Flat
    0.82
     Flat
    0.80
     FLAT
    0.80
     timeframe
    0.80
     waktu
    0.80
    flat
    0.79
    Act Density 0.110%

    No Known Activations