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

    Neuronpedia

    INDEX
    Explanations

    capital letters in a specific formatting pattern

    oai_token-act-pair · gpt-3.5-turbo

    expressions of high intensity or emotional impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     covenant
    -0.61
     sculpt
    -0.60
     star
    -0.58
     trump
    -0.57
     swe
    -0.56
     deaf
    -0.56
     encomp
    -0.55
     overpower
    -0.54
     seeking
    -0.54
     scrap
    -0.54
    POSITIVE LOGITS
    Advertisements
    1.03
    Advertisement
    0.95
    Conclusion
    0.92
    Recommended
    0.90
    Related
    0.90
    If
    0.90
    --------------------------------------------------------
    0.89
    Official
    0.89
    References
    0.89
    Besides
    0.87
    Act Density 0.844%

    No Known Activations