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

    Neuronpedia

    INDEX
    Explanations

    action-related words and phrases, such as verbs related to movement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.71
    reements
    -0.67
     pronounced
    -0.64
    catentry
    -0.62
     provocation
    -0.62
    idental
    -0.58
    ervation
    -0.58
    OTOS
    -0.58
    attribute
    -0.57
    usable
    -0.57
    POSITIVE LOGITS
     onward
    1.15
     uphill
    1.14
     toward
    1.14
     onwards
    1.12
     towards
    1.11
     downhill
    1.09
     away
    1.07
     through
    1.04
     across
    1.01
     ashore
    1.00
    Act Density 0.155%

    No Known Activations