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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opposition or disagreement with certain topics or positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "oppose" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Golf
    -0.67
     Meal
    -0.67
    fect
    -0.60
     Quant
    -0.59
     Rolls
    -0.59
     drying
    -0.59
     Guru
    -0.59
     Cricket
    -0.59
     Logged
    -0.59
    chel
    -0.58
    POSITIVE LOGITS
     oppose
    3.27
     opposes
    2.46
     opposed
    2.08
     disapprove
    1.77
     opposition
    1.56
     opposing
    1.54
     despise
    1.42
     criticize
    1.39
     refute
    1.35
     objected
    1.33
    Act Density 0.011%

    No Known Activations