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

    Neuronpedia

    INDEX
    Explanations

    words related to various societal and political topics, specifically emphasizing the concept of issues, such as political debates, human rights, and controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    discussions surrounding political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammers
    -0.82
    urses
    -0.81
    ramid
    -0.80
    uner
    -0.77
    ramids
    -0.77
    ittle
    -0.73
    ellow
    -0.72
    ãĥ³ãĤ¸
    -0.72
    glas
    -0.72
    ongyang
    -0.71
    POSITIVE LOGITS
     flared
    0.88
     confronting
    0.88
     raised
    0.86
     relating
    0.81
     facing
    0.79
     pertaining
    0.79
     arising
    0.78
     affecting
    0.78
     plag
    0.78
     resolutions
    0.77
    Act Density 0.050%

    No Known Activations