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

    Neuronpedia

    INDEX
    Explanations

    references to titles and names of nobility or aristocracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nobility titles

    np_acts-logits-general · gemini-2.0-flash

    titles of nobility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.76
    évaluateur
    -0.73
    GEBURTS
    -0.73
     Drapeau
    -0.71
     дописавши
    -0.71
     <=",
    -0.67
     Infórmanos
    -0.65
    ]")]
    -0.64
    ."));
    -0.64
     AssemblyProduct
    -0.63
    POSITIVE LOGITS
     Lord
    0.95
    Lord
    0.88
     lord
    0.82
     Lady
    0.75
     Baron
    0.71
     Earl
    0.70
     Sir
    0.69
    Lady
    0.68
     Lords
    0.67
    Sir
    0.66
    Act Density 0.421%

    No Known Activations