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

    Neuronpedia

    INDEX
    Explanations

    mentions of things or actions related to protests or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-related movements or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Halls
    -0.80
    ĸļ
    -0.75
     Pelicans
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    ODY
    -0.70
    shire
    -0.68
    hower
    -0.68
     COUNTY
    -0.65
     Curve
    -0.65
     Maker
    -0.64
    POSITIVE LOGITS
    abortion
    1.11
    war
    1.07
    establishment
    1.05
    hero
    0.90
    anti
    0.89
    overty
    0.87
    measures
    0.86
    strate
    0.86
    jud
    0.86
    actively
    0.82
    Act Density 0.025%

    No Known Activations