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

    Neuronpedia

    INDEX
    Explanations

    mentions of riots or riot-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to riots and rioting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avez
    -0.80
    bourg
    -0.78
    phies
    -0.76
    ĻĤ
    -0.76
    metics
    -0.75
    DonaldTrump
    -0.72
    hran
    -0.71
    sonian
    -0.70
    amacare
    -0.68
    uchin
    -0.67
    POSITIVE LOGITS
     riot
    1.19
     riots
    0.98
     Riot
    0.85
    ous
    0.81
    ously
    0.76
     mobs
    0.73
    naire
    0.73
    ijn
    0.72
     dispers
    0.71
     Fest
    0.70
    Act Density 0.014%

    No Known Activations