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

    Neuronpedia

    INDEX
    Explanations

    references to individuals named George, particularly in a political context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Ladd
    -0.85
     Ladd
    -0.82
    щему
    -0.78
    Fcn
    -0.78
     Roskov
    -0.76
    SCRIBE
    -0.75
    Рек
    -0.74
    atedral
    -0.73
     Ramb
    -0.73
     nguyễn
    -0.73
    POSITIVE LOGITS
     George
    1.58
    George
    1.44
     Georges
    1.37
    george
    1.30
     Georgie
    1.24
     george
    1.23
     GEORGE
    1.20
    Georges
    1.20
    GEORGE
    1.10
     Georgetown
    1.05
    Act Density 0.010%

    No Known Activations