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

    Neuronpedia

    INDEX
    Explanations

    political and governmental terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to opinions and claims made by individuals or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.76
     respectively
    -0.59
    surprisingly
    -0.59
    anwhile
    -0.56
    arthed
    -0.55
    xtap
    -0.52
    described
    -0.51
    translation
    -0.50
    quished
    -0.50
    arnaev
    -0.50
    POSITIVE LOGITS
     ..."
    1.49
     âĢ¦"
    1.40
    %"
    1.35
    ,"
    1.31
    )",
    1.30
    )"
    1.29
    .")
    1.28
    ),"
    1.27
    ..."
    1.23
    ,'"
    1.23
    Act Density 2.005%

    No Known Activations