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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social issues, specifically criticisms and discussions about political figures and events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mentioned
    -0.72
    coins
    -0.62
    eto
    -0.60
    ador
    -0.60
    atin
    -0.58
    agu
    -0.57
    fortunately
    -0.56
    advertising
    -0.55
    umption
    -0.55
    ispers
    -0.55
    POSITIVE LOGITS
     "
    0.67
     legitimate
    0.66
     precursor
    0.63
     deviation
    0.62
     traitor
    0.61
     roadmap
    0.60
     continuum
    0.60
     threat
    0.59
     continuation
    0.59
     gateway
    0.59
    Act Density 17.147%

    No Known Activations