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

    Neuronpedia

    INDEX
    Explanations

    references to social or political protests

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.81
    cester
    -0.81
    bons
    -0.72
    population
    -0.71
    missions
    -0.67
    estone
    -0.66
    oba
    -0.65
    Engineers
    -0.65
    lein
    -0.65
    nosis
    -0.64
    POSITIVE LOGITS
     protests
    0.98
     protesting
    0.82
    unta
    0.81
    ourcing
    0.79
     protesters
    0.79
    hooting
    0.79
     demonstrations
    0.78
     riots
    0.78
     protestors
    0.78
     protest
    0.76
    Act Density 0.025%

    No Known Activations