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

    Neuronpedia

    INDEX
    Explanations

    references to food and dining experiences

    oai_token-act-pair · gpt-3.5-turbo

    events related to dining and social gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     steroids
    -0.78
     suing
    -0.72
     Himself
    -0.72
     dies
    -0.71
     steroid
    -0.70
     Conquer
    -0.70
     epile
    -0.68
    cancer
    -0.67
     Nobel
    -0.66
     implanted
    -0.66
    POSITIVE LOGITS
     downstairs
    0.95
     parked
    0.88
     Parking
    0.87
     cautiously
    0.85
     boarded
    0.82
     parking
    0.80
    artment
    0.80
    CHAPTER
    0.80
     downtown
    0.80
     sleepy
    0.78
    Act Density 0.493%

    No Known Activations