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

    Neuronpedia

    INDEX
    Explanations

    references to specific codes or indicators related to data structures or protocol definitions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     resourceCulture
    -1.00
     مرئيه
    -0.98
    الحياه
    -0.94
    GraphicsUnit
    -0.91
     виправивши
    -0.91
    RenderAtEndOf
    -0.90
    principalColumn
    -0.88
     дописавши
    -0.88
     NSCoder
    -0.88
    writeField
    -0.85
    POSITIVE LOGITS
     E
    0.56
     An
    0.52
     A
    0.50
     I
    0.49
    <eos>
    0.48
     S
    0.47
     game
    0.47
     Ex
    0.47
     in
    0.46
     of
    0.46
    Act Density 0.004%

    No Known Activations