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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or elements related to categories or structures, particularly in a hierarchical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیا
    -0.69
    SourceChecksum
    -0.66
    %</
    -0.65
    ]%
    -0.64
    SpringBootTest
    -0.64
    esserts
    -0.62
    ArgsConstructor
    -0.61
    makeConstraints
    -0.60
    HasForeignKey
    -0.60
    ]$}
    -0.60
    POSITIVE LOGITS
     acrylique
    0.57
    PreferredItem
    0.53
    แล
    0.50
    توض
    0.48
     arada
    0.48
    bbene
    0.48
    참고
    0.48
     Squal
    0.46
     Erzb
    0.46
     réponse
    0.46
    Act Density 0.337%

    No Known Activations