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

    Neuronpedia

    INDEX
    Explanations

    phrases related to customer feedback and company decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pymysql
    -0.71
     uncin
    -0.70
     ftu
    -0.68
     perfet
    -0.68
     poff
    -0.66
     tubercle
    -0.65
     perfon
    -0.64
     ftre
    -0.64
     impegno
    -0.64
     tranf
    -0.64
    POSITIVE LOGITS
     voters
    0.79
     overwhelmingly
    0.67
     popularity
    0.62
     votes
    0.61
     respondents
    0.59
     polls
    0.57
     audiences
    0.57
     audience
    0.56
    popularity
    0.55
     people
    0.55
    Act Density 0.484%

    No Known Activations