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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal actions, charges, and misconduct in official contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.99
    ãĤ¡
    -0.85
    aucuses
    -0.84
    ãĤ¼ãĤ¦ãĤ¹
    -0.81
    ãĥ¼ãĥĨãĤ£
    -0.76
    patch
    -0.76
    ãĥ©ãĥ³
    -0.75
    entimes
    -0.75
    ãĤ¤ãĥĪ
    -0.74
    ãĤ¦ãĤ¹
    -0.73
    POSITIVE LOGITS
     defendants
    0.97
     alleged
    0.93
     whistleblowers
    0.90
     him
    0.88
     disgr
    0.86
     suspects
    0.85
     individuals
    0.85
     accused
    0.84
     perpetrators
    0.84
     wrongdoing
    0.83
    Act Density 0.189%

    No Known Activations