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

    Neuronpedia

    INDEX
    Explanations

    titles and roles associated with leadership or authority positions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     president
    -1.02
    president
    -0.96
     presidents
    -0.85
     chairman
    -0.78
     presidency
    -0.71
    chairman
    -0.69
     presidente
    -0.66
     chairmen
    -0.65
     presiden
    -0.64
     presidential
    -0.63
    POSITIVE LOGITS
     Director
    1.16
     Deputy
    0.99
     Chief
    0.94
     Assistant
    0.91
     Vice
    0.86
     Senior
    0.85
    Deputy
    0.85
     Associate
    0.84
    verwijspagina
    0.83
    Assistant
    0.82
    Act Density 0.080%

    No Known Activations