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

    Neuronpedia

    INDEX
    Explanations

    concepts surrounding equality and fairness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGER
    -0.15
    اÛĮر
    -0.15
     XCTAssert
    -0.14
    inesis
    -0.14
    eros
    -0.14
     exponent
    -0.13
    ARGIN
    -0.13
    elles
    -0.12
    OffsetTable
    -0.12
    lotte
    -0.12
    POSITIVE LOGITS
     equal
    0.94
     Equal
    0.78
    equal
    0.78
     EQUAL
    0.74
    Equal
    0.72
     igual
    0.70
     equality
    0.67
     equals
    0.67
    _equal
    0.62
    .equal
    0.59
    Act Density 0.342%

    No Known Activations