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

    Neuronpedia

    INDEX
    Explanations

    references to specific methods or components in technical descriptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.52
     
    -0.51
     {
    -0.47
    ;
    -0.45
     "
    -0.44
     home
    -0.44
    '
    -0.43
     under
    -0.42
    <bos>
    -0.41
     term
    -0.41
    POSITIVE LOGITS
    تقاوى
    0.85
    Datuak
    0.81
     HasFactory
    0.79
     дописавши
    0.78
     سكانية
    0.76
     AssemblyVersion
    0.75
    webElementGuid
    0.74
    GraphicsUnit
    0.73
    ^(@)
    0.73
     photolibrary
    0.72
    Act Density 0.174%

    No Known Activations