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

    Neuronpedia

    INDEX
    Explanations

    variations of the apostrophe used in contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.99
     Савезне
    -1.52
    '
    -1.43
    ’
    -1.35
     disambiguazione
    -1.22
     виправивши
    -1.17
    ItemBackground
    -1.17
    expandindo
    -1.14
     Мексичка
    -1.13
     AspNetCore
    -1.10
    POSITIVE LOGITS
    ↵
    0.60
    ,
    0.59
    ↵↵
    0.58
     a
    0.57
     you
    0.53
    …
    0.52
     we
    0.51
     …
    0.50
     and
    0.50
     You
    0.49
    Act Density 0.399%

    No Known Activations