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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.40
     Мексичка
    -1.28
    +#+
    -1.24
    Geplaatst
    -1.23
    XmlAccessorType
    -1.18
    <bos>
    -1.16
    WithIOException
    -1.14
     snippetHide
    -1.14
    ⓧ
    -1.14
     للمعارف
    -1.12
    POSITIVE LOGITS
    ↵
    0.72
    ↵↵
    0.71
     
    0.70
    <eos>
    0.64
     You
    0.63
     the
    0.62
    You
    0.59
     \
    0.58
     We
    0.58
    al
    0.56
    Act Density 0.158%

    No Known Activations