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

    Neuronpedia

    INDEX
    Explanations

    references to documents, inventions, and technical or engineering-related content

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.01
    msgTypes
    -0.78
    RenderAtEndOf
    -0.70
    awtextra
    -0.59
    fjspx
    -0.59
     Carlyle
    -0.58
    раздо
    -0.58
    UserScript
    -0.57
    principalTable
    -0.56
     ujednoznacz
    -0.56
    POSITIVE LOGITS
    τως
    0.47
    >//
    0.46
    elow
    0.46
    Atsauces
    0.46
    MigrationBuilder
    0.46
    Ārējās
    0.46
    ]=="
    0.46
    Этот
    0.45
     suya
    0.44
    This
    0.43
    Act Density 0.069%

    No Known Activations