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

    Neuronpedia

    INDEX
    Explanations

    numerical data such as measurements, percentages, and values

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aband
    -0.71
    otropic
    -0.71
    ullivan
    -0.69
    uther
    -0.69
    opol
    -0.67
    nos
    -0.66
    romy
    -0.65
    rahim
    -0.65
    otin
    -0.64
    bull
    -0.63
    POSITIVE LOGITS
     ratio
    0.93
     coefficient
    0.88
     difference
    0.85
     squared
    0.85
     ratios
    0.83
     ratings
    0.83
     rating
    0.81
     coefficients
    0.80
     ranges
    0.80
     totals
    0.78
    Act Density 0.321%

    No Known Activations