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

    Neuronpedia

    INDEX
    Explanations

    phrases related to representation or lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to representation in various contexts, particularly related to social and cultural themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cake
    -0.79
    launch
    -0.74
    urst
    -0.74
    awar
    -0.74
    strap
    -0.73
    imb
    -0.68
    stead
    -0.67
    sis
    -0.67
    sterdam
    -0.65
    hib
    -0.65
    POSITIVE LOGITS
     Represent
    1.03
     representation
    0.94
    ational
    0.92
    ATIVE
    0.90
    atively
    0.89
    eering
    0.86
    ative
    0.86
     representations
    0.85
    DonaldTrump
    0.80
    represented
    0.78
    Act Density 0.031%

    No Known Activations