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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific array bracket formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    幸
    -0.52
    切
    -0.49
    前
    -0.48
    الإنجليزية
    -0.46
    截
    -0.46
    <eos>
    -0.45
    gde
    -0.45
     }{@
    -0.44
    তথ্যসূত্র
    -0.43
    fpm
    -0.42
    POSITIVE LOGITS
    ,:),
    0.64
    .}(
    0.61
    tellations
    0.60
     ewig
    0.59
    rizona
    0.59
    titian
    0.59
     kasarigan
    0.58
    Населення
    0.57
     الرياضيه
    0.56
    RegressionTest
    0.56
    Act Density 0.004%

    No Known Activations