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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    references to the direction "south."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MFT
    -0.87
    TABLE
    -0.81
    wcsstore
    -0.77
    Legendary
    -0.77
    brance
    -0.76
     CLSID
    -0.76
    PRESS
    -0.75
    inventoryQuantity
    -0.75
     "$:/
    -0.74
    soDeliveryDate
    -0.74
    POSITIVE LOGITS
    ward
    1.16
    west
    1.03
    wards
    0.96
     hemisphere
    0.94
     west
    0.93
     east
    0.90
    side
    0.90
    wind
    0.88
    wark
    0.87
    western
    0.87
    Act Density 0.018%

    No Known Activations