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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical analysis and bias in medical data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     I
    -0.61
                                   
    -0.60
      
    -0.59
    …
    -0.58
     =
    -0.56
     en
    -0.56
    ↵
    -0.56
     y
    -0.56
    <eos>
    -0.54
     r
    -0.54
    POSITIVE LOGITS
    WebVitals
    1.27
     Efq
    1.09
     مشين
    1.05
    MLLoader
    1.05
     Majefty
    1.05
    ſelves
    1.03
     архивлан
    1.02
     arşivlendi
    1.01
    ſelf
    1.00
     оригіналу
    1.00
    Act Density 2.252%

    No Known Activations