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

    Neuronpedia

    INDEX
    Explanations

    text that is formatted with bold tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.74
    ''');
    -0.62
    IsContent
    -0.61
    ยก
    -0.57
    öp
    -0.56
    ificance
    -0.55
     Vara
    -0.54
     Wikispecies
    -0.53
    öscht
    -0.53
     indisponible
    -0.53
    POSITIVE LOGITS
    <strong>
    1.42
    <em>
    1.22
    <b>
    1.04
    <u>
    1.00
    <code>
    0.96
     auroit
    0.90
    <s>
    0.88
    <sub>
    0.86
    </strong>
    0.82
    ungkinan
    0.81
    Act Density 0.016%

    No Known Activations