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

    Neuronpedia

    INDEX
    Explanations

    single-character symbols or markup formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )");
    -0.91
     nakalista
    -0.88
    "]];
    -0.87
    RegressionTest
    -0.83
    Bronnen
    -0.77
    ()));
    -0.76
    ]");
    -0.75
    )++;
    -0.75
     transférez
    -0.74
    :])
    -0.73
    POSITIVE LOGITS
     Flushing
    0.52
    parseColor
    0.52
     pri
    0.50
     Kier
    0.50
     privées
    0.49
    zal
    0.49
     بوی
    0.47
    SocketAddress
    0.47
    Kier
    0.47
    rose
    0.47
    Act Density 0.034%

    No Known Activations