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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Williams" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     SND
    -0.89
     Aes
    -0.77
    ]};
    -0.76
     Cuenca
    -0.76
     Metzger
    -0.75
     Collingwood
    -0.75
     datasource
    -0.74
     MTL
    -0.74
     cauſe
    -0.74
    kloped
    -0.73
    POSITIVE LOGITS
     Williams
    2.00
    Williams
    1.75
     WILLIAMS
    1.51
     williams
    1.43
    williams
    1.40
    WILLIAM
    1.21
     Williamsburg
    1.14
     William
    1.11
     Williamson
    1.02
    William
    1.02
    Act Density 0.008%

    No Known Activations