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

    Neuronpedia

    INDEX
    Explanations

    names related to individuals in news events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aries
    -0.81
    chnology
    -0.71
    20439
    -0.70
    MpServer
    -0.70
    essee
    -0.68
    yards
    -0.67
    hire
    -0.67
    eries
    -0.62
    naires
    -0.62
    naire
    -0.62
    POSITIVE LOGITS
     Ali
    1.13
     Hassan
    1.05
     bin
    1.00
     ibn
    0.99
     Bin
    0.96
    hammad
    0.95
     Ibrahim
    0.95
     Mohamed
    0.93
     Yun
    0.91
     Jamal
    0.91
    Act Density 0.020%

    No Known Activations