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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases or contextual markers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.20
    GraphicsUnit
    -1.02
    ValueStyle
    -0.99
     оригіналу
    -0.87
    InjectAttribute
    -0.84
    تقاوى
    -0.83
     consultato
    -0.83
     المعيارى
    -0.82
    EndGlobalSection
    -0.81
     doInBackground
    -0.81
    POSITIVE LOGITS
     tips
    0.66
     Top
    0.54
    tips
    0.52
     top
    0.52
    Top
    0.49
     ways
    0.49
    str
    0.48
     Str
    0.48
    prop
    0.47
     TOP
    0.46
    Act Density 0.095%

    No Known Activations