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

    Neuronpedia

    INDEX
    Explanations

    references to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    indications of violence or criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NASA
    -0.88
    CNN
    -0.85
    azeera
    -0.81
    WASHINGTON
    -0.78
    braska
    -0.77
    Britain
    -0.76
    Syria
    -0.75
    olkien
    -0.74
    agu
    -0.74
    20439
    -0.73
    POSITIVE LOGITS
     patrons
    1.65
     customers
    1.56
     propriet
    1.52
     employees
    1.52
     regulars
    1.42
     customer
    1.42
     staff
    1.37
     employee
    1.35
     Customers
    1.28
     guests
    1.28
    Act Density 0.635%

    No Known Activations