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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and concepts related to theory verification and discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.71
    RenderAtEndOf
    -0.64
    ModelSerializer
    -0.60
    الحياه
    -0.59
    Життєпис
    -0.56
     ligiloj
    -0.56
    Hentet
    -0.55
    ItemBackground
    -0.54
     Chwiliwch
    -0.53
    .*")]
    -0.53
    POSITIVE LOGITS
     scientific
    0.92
     wissenschaft
    0.83
     scientifically
    0.80
     bilim
    0.74
     science
    0.72
     refuted
    0.71
     Scientific
    0.71
    scientific
    0.69
     científicos
    0.68
     scientifique
    0.67
    Act Density 1.418%

    No Known Activations