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

    Neuronpedia

    INDEX
    Explanations

    phrases related to topics or themes in books or movies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific titles and themes of books or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carney
    -0.48
    inar
    -0.47
     largeDownload
    -0.46
    committee
    -0.45
     Applicant
    -0.45
    imester
    -0.44
     meanwhile
    -0.44
    amination
    -0.43
     Ank
    -0.42
     objected
    -0.40
    POSITIVE LOGITS
     and
    0.78
     AND
    0.60
     &
    0.60
     or
    0.57
    ulously
    0.55
    and
    0.53
    .</
    0.50
    ,...
    0.50
     unforgettable
    0.48
    ®,
    0.47
    Act Density 1.641%

    No Known Activations