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

    Neuronpedia

    INDEX
    Explanations

    phrases related to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of days in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untled
    -0.74
    urus
    -0.72
    ifice
    -0.72
    acus
    -0.67
    athy
    -0.65
    XT
    -0.62
    ignty
    -0.62
    ingu
    -0.62
    urities
    -0.61
    asso
    -0.61
    POSITIVE LOGITS
     weekend
    0.88
    iversary
    0.87
     hiatus
    0.82
     affair
    0.80
     Advent
    0.78
     anniversary
    0.76
     trip
    0.76
     stretch
    0.74
     consultations
    0.73
     interval
    0.72
    Act Density 0.043%

    No Known Activations