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

    Neuronpedia

    INDEX
    Explanations

    technical specifications such as network speeds and data storage measurements

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements and units of measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matically
    -0.76
     scrut
    -0.65
    ukong
    -0.64
    yah
    -0.63
    stad
    -0.61
    yang
    -0.61
    bery
    -0.60
    icably
    -0.60
     VIDEOS
    -0.59
    zona
    -0.59
    POSITIVE LOGITS
    ²
    0.85
     Ratio
    0.84
     ratio
    0.82
    )=(
    0.73
    mare
    0.71
    inion
    0.67
     converter
    0.64
    erness
    0.64
    tenance
    0.64
     ratios
    0.62
    Act Density 0.113%

    No Known Activations