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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explaining or indicating something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reluct
    -1.96
     unden
    -1.96
     encomp
    -1.88
     increa
    -1.88
     disagre
    -1.88
     fta
    -1.88
     guarante
    -1.87
     wherea
    -1.85
     secon
    -1.84
     inev
    -1.84
    POSITIVE LOGITS
    <bos>
    1.23
     JpaRepository
    0.69
     normal
    0.67
    ResponseWriter
    0.66
    HtmlAttribute
    0.65
    complexContent
    0.64
    XMLSchema
    0.64
     createState
    0.63
     harmless
    0.63
    正常
    0.62
    Act Density 0.433%

    No Known Activations