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

    Neuronpedia

    INDEX
    Explanations

    information related to newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to additional content or newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kamp
    -0.72
    pex
    -0.64
    atan
    -0.62
    ongyang
    -0.60
    lihood
    -0.60
     Examination
    -0.58
     Classification
    -0.57
    Enlarge
    -0.56
     whichever
    -0.56
    thora
    -0.54
    POSITIVE LOGITS
     newsletters
    1.03
    thumbnails
    0.73
     subscribers
    0.69
     subscriptions
    0.67
     articles
    0.66
     content
    0.65
    videos
    0.64
     exciting
    0.63
     stories
    0.63
     goodies
    0.61
    Act Density 0.009%

    No Known Activations