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

    Neuronpedia

    INDEX
    Explanations

    references to legal or governmental documents

    oai_token-act-pair · gpt-3.5-turbo

    references to legal constitutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stun
    -0.74
     Mile
    -0.71
     Truck
    -0.69
     Customers
    -0.68
     Vill
    -0.68
     Yards
    -0.67
     Lank
    -0.67
     Detect
    -0.67
     Relationship
    -0.66
     Territories
    -0.66
    POSITIVE LOGITS
    ality
    1.21
    uary
    1.02
     constitution
    0.95
    alities
    0.93
    eering
    0.92
    utive
    0.92
    ically
    0.90
    oru
    0.82
    eers
    0.80
    ally
    0.79
    Act Density 0.009%

    No Known Activations