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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical data and citations in legal or technical documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     mellitus
    -0.93
     FontWeight
    -0.77
    PostBack
    -0.74
     Tade
    -0.72
     Trey
    -0.71
     Thackeray
    -0.66
     Patricio
    -0.64
     planas
    -0.64
     argint
    -0.63
     Tadeusz
    -0.63
    POSITIVE LOGITS
    Portály
    0.81
    ollectionView
    0.81
    rfloor
    0.73
    ColumnHeaders
    0.72
     Lons
    0.71
    澈
    0.70
     setInterval
    0.70
     виправивши
    0.70
    كويكب
    0.70
     Consist
    0.70
    Act Density 0.271%

    No Known Activations