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

    Neuronpedia

    INDEX
    Explanations

    names or titles of political leaders

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icular
    -0.89
    zsche
    -0.86
    uckland
    -0.81
    iscopal
    -0.77
    yt
    -0.75
    entric
    -0.74
    worldly
    -0.73
    ãĤ¨ãĥ«
    -0.73
    adr
    -0.72
     worldly
    -0.71
    POSITIVE LOGITS
     Majority
    1.08
     Leader
    1.06
     Whip
    0.94
     Voice
    0.84
     Minority
    0.83
     Senator
    0.83
     Chairman
    0.81
     Chair
    0.81
     Hue
    0.79
     Floor
    0.78
    Act Density 0.015%

    No Known Activations