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

    Neuronpedia

    INDEX
    Explanations

    locations or positions within a physical setting, such as behind a specific object

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    votes
    -0.85
    Events
    -0.84
     assessments
    -0.80
     incomes
    -0.79
     estimates
    -0.78
     Governments
    -0.77
     answers
    -0.76
    views
    -0.76
     visas
    -0.76
    agents
    -0.76
    POSITIVE LOGITS
     bunch
    0.96
     doorway
    0.95
    rouse
    0.95
     pile
    0.94
     hole
    0.93
     pedest
    0.92
     handful
    0.91
     mound
    0.89
     nearby
    0.88
     suitcase
    0.87
    Act Density 0.322%

    No Known Activations