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

    Neuronpedia

    INDEX
    Explanations

    statements emphasizing actions or roles played by individuals within the legal or political systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unspeak
    -1.06
     maneu
    -1.01
     shenan
    -1.01
     volunte
    -0.94
     impra
    -0.94
     ineffec
    -0.94
     practition
    -0.92
     encomp
    -0.92
     disagre
    -0.92
     miscon
    -0.91
    POSITIVE LOGITS
    <bos>
    0.95
     him
    0.94
     us
    0.85
     me
    0.75
     them
    0.73
    him
    0.71
    setViewportView
    0.69
     hini
    0.68
     initComponents
    0.66
     AssemblyCompany
    0.66
    Act Density 0.392%

    No Known Activations