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

    Neuronpedia

    INDEX
    Explanations

    curly quotation marks and similar punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mäßig
    -0.66
     abstrait
    -0.64
    ----
    -0.64
     ________
    -0.62
    ătoare
    -0.60
     ----
    -0.60
     légitime
    -0.57
     chrétien
    -0.57
     فريبيس
    -0.57
     चीज़ों
    -0.56
    POSITIVE LOGITS
    »
    3.01
    )»
    2.77
    ?»
    2.76
    .»
    2.73
    ,»
    2.63
    ».
    2.62
    »,
    2.60
     »
    2.59
    !»
    2.53
    »)
    2.48
    Act Density 0.089%

    No Known Activations