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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly apostrophes and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.94
    Diweddarwch
    -0.65
    Abitanti
    -0.61
     Rine
    -0.60
     disambiguazione
    -0.56
     bezeichneter
    -0.55
     مواليد
    -0.54
    回事
    -0.54
     kaarangay
    -0.52
     صوتيه
    -0.52
    POSITIVE LOGITS
    s
    1.00
    )’
    0.94
    .’
    0.86
     vostri
    0.78
    ,’
    0.76
    !’
    0.74
    (‘
    0.71
    .’”
    0.71
    …’
    0.71
    ?’
    0.71
    Act Density 0.206%

    No Known Activations