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

    Neuronpedia

    INDEX
    Explanations

    numeric data or numerical references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Qu
    -0.52
     apparently
    -0.51
    хи
    -0.48
     almost
    -0.47
    دن
    -0.46
     supposedly
    -0.45
    qu
    -0.44
    ssch
    -0.43
     in
    -0.43
    ul
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    1.06
    expandindo
    0.92
     resourceCulture
    0.91
     /\.
    0.88
    ValueStyle
    0.85
     pinulongan
    0.85
     متعلقه
    0.84
    AndEndTag
    0.83
    fjspx
    0.83
     المعيارى
    0.81
    Act Density 0.028%

    No Known Activations