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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases indicating questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.75
    ãĤ´ãĥ³
    -0.75
    etheless
    -0.69
    '>
    -0.68
    xtap
    -0.68
    ãĢij
    -0.68
    Oracle
    -0.66
    pload
    -0.62
    ËĪ
    -0.62
    ](
    -0.62
    POSITIVE LOGITS
    ,"
    2.30
    ),"
    2.02
    .,"
    2.01
    ,'"
    1.95
    ',"
    1.94
    ,''
    1.83
    "),
    1.75
    ",
    1.69
     ,"
    1.64
    )",
    1.58
    Act Density 0.709%

    No Known Activations