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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions like durations and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating timeframes and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥī
    -0.69
    ãĤ«
    -0.66
    ãĥķãĤ¡
    -0.62
    ranch
    -0.61
    ivo
    -0.59
    iva
    -0.59
    awaru
    -0.58
    Reviewer
    -0.56
    ãĥ¼
    -0.55
    brow
    -0.55
    POSITIVE LOGITS
     weeks
    1.73
     months
    1.70
    months
    1.59
     days
    1.52
     hours
    1.50
    hours
    1.43
     Months
    1.37
     fifteen
    1.35
     years
    1.35
     fortnight
    1.33
    Act Density 0.596%

    No Known Activations