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

    Neuronpedia

    INDEX
    Explanations

    occurrences of backticks and code-related syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %)$
    -0.73
    adaptiveStyles
    -0.71
    ouml
    -0.69
    ViewFeatures
    -0.66
    ++
    -0.63
    es
    -0.62
    '))
    -0.62
    ')))
    -0.59
    tamentos
    -0.59
    esen
    -0.58
    POSITIVE LOGITS
    theless
    1.05
    </th>
    0.82
     Ather
    0.79
    页面存档备份
    0.75
    .`
    0.75
     anúncio
    0.72
    <h6>
    0.72
    ization
    0.71
    (`/
    0.71
     HTT
    0.69
    Act Density 0.264%

    No Known Activations