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

    Neuronpedia

    INDEX
    Explanations

    statements of importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anth
    -0.71
    ullivan
    -0.68
    avi
    -0.63
    NetMessage
    -0.62
    lip
    -0.61
    iliate
    -0.59
    olson
    -0.59
    ãĤ¼ãĤ¦ãĤ¹
    -0.58
    chrome
    -0.56
    opolis
    -0.56
    POSITIVE LOGITS
     applauded
    1.20
     ashamed
    1.13
     avoided
    1.13
     congratulated
    0.99
     recons
    0.99
    fitting
    0.94
     thanking
    0.91
     regarded
    0.90
     abolished
    0.89
     viewed
    0.88
    Act Density 0.114%

    No Known Activations