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

    Neuronpedia

    INDEX
    Explanations

    the action of starting or beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate an action or process starting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.62
    quickShipAvailable
    -0.62
    enance
    -0.61
     Compass
    -0.60
    abiding
    -0.60
    afety
    -0.60
     Guardian
    -0.59
     Explan
    -0.58
    soDeliveryDate
    -0.58
    grounds
    -0.58
    POSITIVE LOGITS
     accumulate
    1.02
     scratch
    0.90
     compensate
    0.87
     explore
    0.87
     settle
    0.86
     dismantle
    0.86
     unravel
    0.83
     squeeze
    0.82
     earn
    0.82
     regain
    0.82
    Act Density 0.067%

    No Known Activations