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

    Neuronpedia

    INDEX
    Explanations

    references to rules, regulations, and compliance standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.52
     "..\..\..\
    -0.52
    BeginContext
    -0.52
    usermodel
    -0.51
     disambiguazione
    -0.51
    cellona
    -0.49
    option
    -0.48
    hoe
    -0.48
    рее
    -0.48
     cherchés
    -0.48
    POSITIVE LOGITS
     imposed
    1.21
     enforced
    1.13
     governing
    1.00
     established
    0.95
     ditetapkan
    0.95
    imposed
    0.94
     dictated
    0.93
     laid
    0.93
     establecido
    0.92
     establecidos
    0.90
    Act Density 0.492%

    No Known Activations