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

    Neuronpedia

    INDEX
    Explanations

    technical or legal terminology related to documents and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McGovern
    -0.85
     Batavia
    -0.83
    ждую
    -0.83
     Mollus
    -0.83
    rahi
    -0.78
    RegressionTest
    -0.78
     kæ
    -0.77
    rolid
    -0.76
     Metzger
    -0.76
     rempli
    -0.76
    POSITIVE LOGITS
    ="'.$
    0.86
     '}
    0.77
     ?'
    0.73
    ]';
    0.73
     Urqu
    0.73
     Arlene
    0.71
    arashtra
    0.69
     wees
    0.69
    Edges
    0.68
    )";
    0.67
    Act Density 11.701%

    No Known Activations