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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and potentially numbers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.60
    Tembelea
    -0.53
     eleventh
    -0.53
     Walters
    -0.52
    arov
    -0.52
    putAll
    -0.51
    hals
    -0.50
    idon
    -0.49
     ويكيميديا
    -0.49
     Purcell
    -0.49
    POSITIVE LOGITS
     ThemeData
    0.79
    MemoryWarning
    0.77
    ThroughAttribute
    0.70
     GenerationType
    0.66
     AssemblyCompany
    0.66
    makeConstraints
    0.63
     оригіналу
    0.63
     RSSSF
    0.62
    ViewImports
    0.59
     <<<<<<<<<<<<<<
    0.59
    Act Density 0.078%

    No Known Activations