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

    Neuronpedia

    INDEX
    Explanations

    assertive statements about emotional well-being and human experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.86
     kasarigan
    -0.86
    :✨
    -0.81
    +#+
    -0.81
     autorytatywna
    -0.81
     Paglinawan
    -0.80
    ,:);
    -0.78
    下载附件
    -0.78
    XmlAccessorType
    -0.77
     ModelExpression
    -0.75
    POSITIVE LOGITS
    <strong>
    0.81
    <em>
    0.76
    <blockquote>
    0.65
    <i>
    0.64
    <b>
    0.57
    ↵↵
    0.57
    <sub>
    0.55
    <sup>
    0.55
    <h2>
    0.54
    <h3>
    0.53
    Act Density 0.130%

    No Known Activations