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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation, specifically focusing on periods, commas, and dashes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    těte
    -0.50
    PathParam
    -0.49
    protoc
    -0.49
    fortawesome
    -0.48
     enca
    -0.45
    point
    -0.44
    ínű
    -0.44
    őbb
    -0.43
    تفصیلات
    -0.42
    ьаж
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    0.63
     CGSize
    0.63
     Causeway
    0.63
    μως
    0.62
    SPARENT
    0.61
    >'
    0.61
    ofire
    0.61
    ilever
    0.60
     '+':
    0.60
    WithIOException
    0.59
    Act Density 0.011%

    No Known Activations