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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values and numeric-related operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    prüche
    -0.63
     المعيارى
    -0.62
     Италијани
    -0.60
    ciatore
    -0.58
    كويكب
    -0.57
     חיצוניים
    -0.57
     bershka
    -0.57
     fratelli
    -0.54
    RegressionTest
    -0.53
    rungsseite
    -0.53
    POSITIVE LOGITS
    sizeCache
    0.64
     lenker
    0.56
    principalColumn
    0.54
     MediatR
    0.51
    basicConfig
    0.51
    
    0.50
    PagerAdapter
    0.50
     contextLoads
    0.49
    Бахар
    0.47
    ScreenState
    0.47
    Act Density 0.053%

    No Known Activations