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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "anti"

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-campaigns or movements against various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Halls
    -0.76
    ĸļ
    -0.76
    ODY
    -0.68
     Pelicans
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    hower
    -0.62
    shire
    -0.62
    INGS
    -0.62
    hetti
    -0.62
     transcripts
    -0.62
    POSITIVE LOGITS
    establishment
    1.07
    abortion
    1.05
    war
    1.03
    hero
    0.92
    strate
    0.90
    measures
    0.89
    overty
    0.87
    anti
    0.86
    drug
    0.86
    jud
    0.84
    Act Density 0.025%

    No Known Activations