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

    Neuronpedia

    INDEX
    Explanations

    structured sections and headings in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SwitchCompat
    -0.90
     للمعارف
    -0.88
    Kjelder
    -0.83
    ſelves
    -0.81
     Roskov
    -0.80
     disambiguazione
    -0.78
     otomatig
    -0.77
    gameserver
    -0.75
    elemField
    -0.74
    tanleria
    -0.74
    POSITIVE LOGITS
    <h4>
    0.70
    <h3>
    0.63
    <h2>
    0.56
    <th>
    0.56
    ngo
    0.54
    subsubsection
    0.53
    ＜
    0.51
    <strong>
    0.50
    </h4>
    0.49
    <b>
    0.49
    Act Density 0.136%

    No Known Activations