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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating conflict or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to opposition or resistance against various entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornia
    -0.66
    ayette
    -0.65
    join
    -0.64
    ffe
    -0.64
     Address
    -0.63
    eret
    -0.63
    tymology
    -0.63
    shire
    -0.63
    notes
    -0.62
    markets
    -0.62
    POSITIVE LOGITS
     backdrop
    1.72
     wall
    0.77
     odds
    0.77
     presumption
    0.76
     tyranny
    0.76
     onslaught
    0.75
     encro
    0.75
     advancing
    0.74
     perceived
    0.73
     prejudice
    0.73
    Act Density 0.258%

    No Known Activations