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

    Neuronpedia

    INDEX
    Explanations

    references to noble titles and historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    439
    -0.17
    iber
    -0.15
    ands
    -0.15
    enberg
    -0.15
     opposite
    -0.14
    âĢĮ
    -0.14
    anda
    -0.14
     Suspension
    -0.14
    eced
    -0.14
    .same
    -0.14
    POSITIVE LOGITS
     Lord
    0.27
     Prince
    0.21
    Lord
    0.21
     lord
    0.19
     Governor
    0.18
     Master
    0.18
     LORD
    0.18
     King
    0.18
     Baron
    0.17
     Bishop
    0.16
    Act Density 0.075%

    No Known Activations