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

    Neuronpedia

    INDEX
    Explanations

    presence of subscription-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     expected
    -0.99
     expectation
    -0.97
     expectations
    -0.90
    expected
    -0.90
    expectations
    -0.87
    expectation
    -0.86
     Expected
    -0.84
     expecting
    -0.77
     unexpected
    -0.76
    Expected
    -0.76
    POSITIVE LOGITS
    adpleegd
    0.51
    KURZBESCHREIBUNG
    0.48
     daqui
    0.47
    queryInterface
    0.46
     Protección
    0.45
     acrylique
    0.43
    客様
    0.43
     pasado
    0.43
     Progressive
    0.43
     poivre
    0.42
    Act Density 0.135%

    No Known Activations