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

    Neuronpedia

    INDEX
    Explanations

    words related to geopolitical events, political figures, and government actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -1.37
    ĸļ
    -1.32
     Halls
    -1.11
     Dickens
    -1.04
     Gorge
    -0.96
     Granger
    -0.94
     Brooks
    -0.93
    owship
    -0.93
     Twain
    -0.92
     Timeline
    -0.92
    POSITIVE LOGITS
    digy
    1.94
    verbs
    1.61
    dding
    1.48
    pelling
    1.46
    ccess
    1.42
    strate
    1.41
    ctor
    1.39
    hovah
    1.38
    actively
    1.35
    pping
    1.32
    Act Density 0.333%

    No Known Activations