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

    Neuronpedia

    INDEX
    Explanations

    keywords related to technology and data, such as "pixel", "core counts", "blood sugar", "manufacturing", "cell", "prison populations", and "land prices"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistics and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odcast
    -0.72
    parser
    -0.68
    idav
    -0.67
    icians
    -0.67
    pered
    -0.66
    gently
    -0.65
    »Ĵ
    -0.65
    ascript
    -0.63
    signed
    -0.63
    gans
    -0.62
    POSITIVE LOGITS
     density
    1.15
     capacity
    1.09
     expectancy
    1.08
     intensity
    1.06
     rate
    1.06
     volume
    1.04
     footprint
    1.04
     throughput
    1.04
    ensity
    1.03
     diameter
    1.01
    Act Density 0.494%

    No Known Activations