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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific format indicators and structural elements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -1.50
     '\\;'
    -1.19
    HideFlags
    -1.19
    elemField
    -1.10
    хьтан
    -1.10
    GEBURTSDATUM
    -1.06
    ItemBackground
    -1.03
    EDEFAULT
    -1.03
    WebElementEntity
    -1.03
     Efq
    -1.02
    POSITIVE LOGITS
    \
    1.01
      
    0.87
    <tr>
    0.83
    <strong>
    0.81
    </em>
    0.80
    [toxicity=0]
    0.78
    .
    0.77
    <b>
    0.77
     I
    0.73
    ↵
    0.73
    Act Density 0.006%

    No Known Activations