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

    Neuronpedia

    INDEX
    Explanations

    titles of books or works related to politics or current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shewn
    -0.94
     withal
    -0.89
     friable
    -0.86
     unve
    -0.83
     tolerably
    -0.82
     sessionId
    -0.81
     effectually
    -0.80
     resultList
    -0.79
    <bos>
    -0.78
     createdBy
    -0.75
    POSITIVE LOGITS
     Strukt
    1.00
     Antik
    0.93
     confé
    0.93
     Kategor
    0.90
     biograf
    0.89
     Konkur
    0.88
     Gouver
    0.87
     Interne
    0.85
     alberto
    0.84
     :
    0.84
    Act Density 0.247%

    No Known Activations