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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically parentheses, in the text

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

    parentheses and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    -0.42
     (-
    -0.40
     –
    -0.38
    x
    -0.34
    (-
    -0.34
     y
    -0.33
     η
    -0.32
    ↵↵
    -0.31
     x
    -0.30
    {-
    -0.30
    POSITIVE LOGITS
    httphttps
    0.91
     OMITBAD
    0.84
     Weiſe
    0.83
    ScopeManager
    0.81
    majánló
    0.81
    ніципа
    0.80
    parsedMessage
    0.80
    <unused3>
    0.79
    <pad>
    0.79
    <unused21>
    0.79
    Act Density 0.175%

    No Known Activations