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

    Neuronpedia

    INDEX
    Explanations

    mentions of political parties, particularly the "Liberals" and the "Tories"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political parties, particularly the Liberals and Tories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļé
    -0.67
     visitation
    -0.66
    ographer
    -0.66
    noon
    -0.64
    states
    -0.63
    Condition
    -0.63
    Planet
    -0.62
    ty
    -0.62
     Janeiro
    -0.62
    plet
    -0.58
    POSITIVE LOGITS
    ervatives
    1.28
    ervative
    1.21
    hift
    1.11
    aurus
    1.08
    paces
    1.07
    mith
    0.98
    heet
    0.93
    chool
    0.86
    hip
    0.85
    ongs
    0.81
    Act Density 0.019%

    No Known Activations