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 time periods and durations of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     slightest
    -0.86
    reci
    -0.73
    prints
    -0.70
    orkshire
    -0.68
     positives
    -0.67
    cest
    -0.66
    ittens
    -0.65
    tics
    -0.62
     detectors
    -0.61
     equivalents
    -0.60
    POSITIVE LOGITS
     consisting
    1.10
     spanning
    1.06
     involving
    1.00
     dubbed
    0.99
     overseen
    0.96
     spearheaded
    0.92
     comprising
    0.89
     culminating
    0.89
     spree
    0.88
     headlined
    0.88
    Act Density 0.380%

    No Known Activations