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

    Neuronpedia

    INDEX
    Explanations

    military ranks and titles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    jury
    -0.71
    SourceFile
    -0.70
    apers
    -0.70
    Consumer
    -0.68
     graft
    -0.68
    Story
    -0.67
    flix
    -0.66
    cats
    -0.66
    rums
    -0.65
    ramid
    -0.65
    POSITIVE LOGITS
     Mattis
    1.14
     Kham
    0.98
     Hasan
    0.95
     Ernest
    0.94
     Abdul
    0.93
     Khalid
    0.91
     William
    0.90
    onnaissance
    0.90
     Marshal
    0.89
     David
    0.87
    Act Density 0.067%

    No Known Activations