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

    Neuronpedia

    INDEX
    Explanations

    keywords related to the French word "que"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "queer" along with related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inately
    -0.80
    lessly
    -0.79
    inating
    -0.77
    uania
    -0.72
     glim
    -0.69
    iaries
    -0.69
    ERAL
    -0.69
    inators
    -0.68
     spacing
    -0.67
     STATS
    -0.67
    POSITIVE LOGITS
    que
    1.07
    odore
    0.83
    erness
    0.83
    edo
    0.83
    lde
    0.80
    zzi
    0.80
    zon
    0.79
    ague
    0.79
    enne
    0.78
    ep
    0.77
    Act Density 0.021%

    No Known Activations