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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Contributions
    -0.78
    tu
    -0.75
     Differences
    -0.74
    olor
    -0.70
    edu
    -0.70
     contributions
    -0.68
     Volunte
    -0.67
     fortunes
    -0.66
     Technologies
    -0.66
     Benefits
    -0.65
    POSITIVE LOGITS
     week
    1.21
     month
    1.14
    week
    1.02
    month
    1.01
     weekday
    1.00
     fortnight
    0.98
     day
    0.94
     calendar
    0.93
    ciating
    0.87
     year
    0.87
    Act Density 0.125%

    No Known Activations