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

    Neuronpedia

    INDEX
    Explanations

    references to yearly reviews and summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.50
    IsContent
    -0.50
    ForValue
    -0.44
    észetes
    -0.42
    PhysRevD
    -0.40
    CppMethod
    -0.39
    goku
    -0.38
     المعيارى
    -0.37
     grø
    -0.36
     "..\..\..\
    -0.36
    POSITIVE LOGITS
    
    0.52
    0.49
     farewell
    0.46
     legado
    0.46
     nostalgic
    0.45
    再见
    0.44
     numerus
    0.44
    années
    0.43
     cherished
    0.42
     Thank
    0.42
    Act Density 0.508%

    No Known Activations