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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical terminology or concepts

    oai_token-act-pair · gpt-3.5-turbo

    themes and references relating to science and scientific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lease
    -0.78
     unwanted
    -0.64
    pload
    -0.60
    WAY
    -0.59
    gui
    -0.57
    anche
    -0.56
    olina
    -0.56
    earances
    -0.56
    hai
    -0.56
    kw
    -0.56
    POSITIVE LOGITS
    士
    0.71
    ĨĴ
    0.68
    ateurs
    0.64
     trig
    0.63
    Lens
    0.63
    cience
    0.63
     sciences
    0.62
    urus
    0.62
     science
    0.61
    STEM
    0.61
    Act Density 1.023%

    No Known Activations