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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation marks, particularly commas and parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.62
     Precambrian
    -0.59
     ſch
    -0.59
     pleaſure
    -0.58
     ſche
    -0.58
     quæ
    -0.57
     ſtate
    -0.57
    valently
    -0.57
     noft
    -0.56
     helse
    -0.55
    POSITIVE LOGITS
     виправивши
    1.06
    parsedMessage
    0.98
    ″]
    0.90
     referenties
    0.89
    }>
    0.85
    ()]
    0.85
    }{*}{}
    0.84
    ">)</
    0.84
    "])
    0.83
    +")
    0.82
    Act Density 0.222%

    No Known Activations