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

    Neuronpedia

    INDEX
    Explanations

    news or announcement headlines

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or postings regarding various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McH
    -0.62
     Cyp
    -0.61
     Tsukuyomi
    -0.59
     Hath
    -0.56
     preceded
    -0.54
     Fields
    -0.54
     Woods
    -0.54
     MacDonald
    -0.54
     Lazarus
    -0.53
    hops
    -0.53
    POSITIVE LOGITS
    everal
    1.02
    ccording
    0.87
    Sorry
    0.87
    Imagine
    0.78
    Reports
    0.77
    Actor
    0.77
    Former
    0.75
    Unless
    0.74
    Despite
    0.74
    Scientists
    0.73
    Act Density 0.066%

    No Known Activations