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

    Neuronpedia

    INDEX
    Explanations

    philosophical arguments and statements made by various individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements made by philosophers and scholars

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    window
    -0.68
    wx
    -0.64
    RELATED
    -0.64
     footprint
    -0.61
    agging
    -0.55
     Manufacturer
    -0.55
    emate
    -0.54
    eve
    -0.54
    hold
    -0.53
     misc
    -0.53
    POSITIVE LOGITS
     eloqu
    0.82
     essays
    0.79
     himself
    0.79
    zsche
    0.76
     aloud
    0.75
     brilliantly
    0.70
     Lect
    0.69
     insightful
    0.68
     succinct
    0.67
     essay
    0.67
    Act Density 0.506%

    No Known Activations