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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    terms related to expectation

    np_token-act-pair-logits · gpt-4o-mini

    expectations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Président
    -0.54
     cuán
    -0.46
    Legende
    -0.46
    rijk
    -0.45
    <%=
    -0.43
    mehl
    -0.43
    iconque
    -0.42
     chưa
    -0.42
    endous
    -0.41
    rijke
    -0.41
    POSITIVE LOGITS
     expected
    0.99
     expectation
    0.94
     EXPECT
    0.92
    expected
    0.90
     Expected
    0.89
     expectations
    0.88
     Expect
    0.87
     expect
    0.85
    Expected
    0.83
    Expect
    0.81
    Act Density 3.525%

    No Known Activations