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

    Neuronpedia

    INDEX
    Explanations

    references to safety and regulatory issues in automobile contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terminology across different domains like programming, engineering, and scientific texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical or documentation-related keywords and phrases (such as programming, code, technical documentation, administrative terminology).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
    Personensuche
    -1.80
    tagHelperRunner
    -1.59
    :✨
    -1.57
     Савезне
    -1.51
     autorytatywna
    -1.48
    kloped
    -1.42
    featureID
    -1.41
    Datuak
    -1.40
    SourceChecksum
    -1.39
    adaptiveStyles
    -1.33
    POSITIVE LOGITS
     
    0.67
    '
    0.62
     […]
    0.57
    ’
    0.54
     and
    0.52
    0.48
    ,
    0.47
    ↵
    0.46
    2
    0.46
    1
    0.46
    Act Density 99.112%
    No Known Activations