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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ----
    -0.83
    -----
    -0.76
    ----------------
    -0.73
    </strong>
    -0.71
     
    -0.70
    --
    -0.68
     "
    -0.67
    ---
    -0.67
    ‐
    -0.65
      
    -0.65
    POSITIVE LOGITS
    )»
    2.19
    ?»
    2.09
    ,»
    2.09
    .»
    1.99
    !»
    1.93
    »,
    1.88
    »-
    1.80
    »)
    1.78
    )».
    1.73
    »?
    1.72
    Act Density 0.103%

    No Known Activations