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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.59
    BASELINE
    -0.59
    Története
    -0.57
    aarrggbb
    -0.56
    ReusableCell
    -0.54
    SharedDtor
    -0.54
    Portale
    -0.54
    Admissions
    -0.52
     مشين
    -0.52
    ότε
    -0.52
    POSITIVE LOGITS
    law
    1.30
     law
    1.29
    laws
    1.12
     laws
    1.11
    LAW
    1.03
    Law
    1.02
     Law
    1.00
     LAW
    0.97
     Laws
    0.92
    Laws
    0.90
    Act Density 0.174%

    No Known Activations