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

    Neuronpedia

    INDEX
    Explanations

    references to a specific political party

    oai_token-act-pair · gpt-3.5-turbo

    references to the NDP (New Democratic Party) and its leaders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ronic
    -0.64
    agic
    -0.61
    abba
    -0.60
    riot
    -0.59
    ai
    -0.58
    ili
    -0.56
    1007
    -0.55
     tort
    -0.55
    illi
    -0.55
    ann
    -0.55
    POSITIVE LOGITS
     NDP
    3.77
     Mulcair
    2.62
     Liberals
    2.21
     RCMP
    2.10
     Liberal
    1.85
     Trudeau
    1.81
     Conservatives
    1.80
     CBC
    1.76
     Alberta
    1.69
     Tories
    1.68
    Act Density 0.014%

    No Known Activations