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

    Neuronpedia

    INDEX
    Explanations

    time-related information denoting comparison or sequence of events in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to events that happened before the current time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ble
    -0.64
    kind
    -0.64
    ggles
    -0.61
    nce
    -0.61
    liga
    -0.59
    Fal
    -0.58
     Scal
    -0.58
    oggles
    -0.58
    Reader
    -0.58
    lua
    -0.57
    POSITIVE LOGITS
     than
    0.80
     earthqu
    0.79
    ivari
    0.74
    actionDate
    0.68
     sidx
    0.66
    aneously
    0.66
    quickShipAvailable
    0.66
     apiece
    0.66
    ascal
    0.64
    than
    0.64
    Act Density 0.044%

    No Known Activations