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

    Neuronpedia

    INDEX
    Explanations

    data related to numerical values and statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     di
    -0.50
     St
    -0.49
     Sen
    -0.47
     em
    -0.45
    -
    -0.45
    go
    -0.44
    St
    -0.44
     them
    -0.44
     wear
    -0.44
     cad
    -0.43
    POSITIVE LOGITS
    MigrationBuilder
    1.54
     propOrder
    1.23
     وتسجيلات
    1.18
     ModelExpression
    1.07
     nahilalakip
    1.02
    RegressionTest
    1.01
     ویکی‌پدی
    0.94
    0.93
     الرياضيه
    0.92
    MLLoader
    0.91
    Act Density 0.106%

    No Known Activations