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

    Neuronpedia

    INDEX
    Explanations

    causal relationships and justifications within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    дыду
    -0.66
    SuppressMessage
    -0.61
    yó
    -0.57
     laten
    -0.49
     spec
    -0.47
     probably
    -0.46
    specs
    -0.46
     specs
    -0.45
    IDAY
    -0.45
    خاص
    -0.45
    POSITIVE LOGITS
     propOrder
    0.85
    ReusableCell
    0.82
    fjspx
    0.82
    TagMode
    0.79
    setVerticalGroup
    0.78
     ویکی‌پدیا
    0.72
    PreInfinity
    0.69
    Geplaatst
    0.68
    StructEnd
    0.68
    üyada
    0.67
    Act Density 0.067%

    No Known Activations