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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political entities, specifically the "House of Representatives."

    oai_token-act-pair · gpt-3.5-turbo

    references to the House of Representatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -1.00
    istically
    -0.84
    zsche
    -0.74
    istic
    -0.74
    fuel
    -0.72
    capital
    -0.72
    illas
    -0.71
    clad
    -0.68
    cash
    -0.68
    company
    -0.66
    POSITIVE LOGITS
     Representatives
    1.00
     Speaker
    0.94
     Appropriations
    0.88
    OTUS
    0.79
    hips
    0.78
     Office
    0.78
    woman
    0.77
    ricting
    0.75
     Representative
    0.74
     Commissioners
    0.74
    Act Density 0.020%

    No Known Activations