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

    Neuronpedia

    INDEX
    Explanations

    references to governmental or diplomatic matters

    oai_token-act-pair · gpt-3.5-turbo

    references to government or political affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĮ
    -0.76
    aneous
    -0.74
    âķIJâķIJ
    -0.70
    âĵĺ
    -0.70
    astic
    -0.69
    ãĥŃ
    -0.68
    ning
    -0.68
    nings
    -0.67
    ש
    -0.67
    thumbnails
    -0.65
    POSITIVE LOGITS
    hips
    0.94
    pring
    0.86
     affairs
    0.81
    mith
    0.80
     departments
    0.78
     committees
    0.77
    chool
    0.75
     bureau
    0.75
     Committee
    0.75
     department
    0.75
    Act Density 0.048%

    No Known Activations