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

    Neuronpedia

    INDEX
    Explanations

    terms related to accuracy and performance metrics in algorithms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.76
    IndentedString
    -0.75
     AssemblyProduct
    -0.74
    parsedMessage
    -0.70
    Captor
    -0.69
    TagMode
    -0.66
    featureID
    -0.63
    SerializedSize
    -0.57
     समीक्षाओं
    -0.55
     Exacts
    -0.55
    POSITIVE LOGITS
     /\.
    0.73
     devil
    0.51
    olybden
    0.50
    hina
    0.49
    oane
    0.48
     mạch
    0.48
    pelier
    0.48
     Gele
    0.47
    abal
    0.47
     Nih
    0.47
    Act Density 0.054%

    No Known Activations