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

    Neuronpedia

    INDEX
    Explanations

    occurrences of time periods, particularly weekly schedules

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to a frequency of occurrence, specifically about actions or events happening weekly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.78
    emort
    -0.65
    ashtra
    -0.65
    ortium
    -0.64
    inav
    -0.63
    amate
    -0.62
    itars
    -0.61
    ected
    -0.60
     acknowled
    -0.59
     constitu
    -0.58
    POSITIVE LOGITS
    days
    1.29
    night
    1.08
    DAY
    1.00
     Ago
    0.88
     ago
    0.88
    iversary
    0.83
    day
    0.79
    orrow
    0.76
     mornings
    0.74
    lies
    0.73
    Act Density 0.044%

    No Known Activations