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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific entities or concepts, like legal injunctions, editorial opinions, or swim workouts, often within longer descriptive contexts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to organizational structures and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clubs
    -0.62
    events
    -0.59
     Machines
    -0.57
     levers
    -0.57
     channels
    -0.56
     Cunning
    -0.55
     Lange
    -0.55
     embassies
    -0.55
     fixtures
    -0.53
    adders
    -0.53
    POSITIVE LOGITS
     consisting
    0.67
    ifier
    0.62
     standpoint
    0.57
     comprised
    0.55
     reader
    0.53
     billboard
    0.53
    hander
    0.52
     perspective
    0.50
     asset
    0.50
    coat
    0.49
    Act Density 0.635%

    No Known Activations