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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate duration or time taken for various actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.95
    hent
    -0.82
    pie
    -0.73
    listed
    -0.72
    ault
    -0.67
    TION
    -0.67
    urable
    -0.67
    Offline
    -0.66
    Leaks
    -0.65
    nc
    -0.65
    POSITIVE LOGITS
     commute
    1.16
     accommodate
    1.11
     compensate
    1.08
     settle
    1.08
     prepare
    1.07
     dedicate
    1.02
     indulge
    1.01
     conserve
    1.00
     locate
    0.97
     make
    0.97
    Act Density 0.185%

    No Known Activations