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

    Neuronpedia

    INDEX
    Explanations

    nutritional information related to diets and calculations

    oai_token-act-pair · gpt-3.5-turbo

    statistical calculations and data metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.78
    gay
    -0.75
    ibi
    -0.75
    edi
    -0.73
    christ
    -0.73
    quit
    -0.69
    iba
    -0.69
    nob
    -0.69
    chat
    -0.69
    chin
    -0.69
    POSITIVE LOGITS
     percentile
    0.88
     subtract
    0.87
     normalized
    0.85
     averaging
    0.85
     descending
    0.83
     multiplying
    0.80
     percentages
    0.80
     ascending
    0.80
     averages
    0.75
     proportional
    0.74
    Act Density 0.267%

    No Known Activations