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

    Neuronpedia

    INDEX
    Explanations

    the symbol 'Ċ' throughout the document

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of high activity or significance within a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Satoshi
    -0.58
     unm
    -0.58
     aging
    -0.58
     triple
    -0.58
     ric
    -0.57
     intending
    -0.56
     pressing
    -0.56
    roth
    -0.56
     hust
    -0.54
    atis
    -0.54
    POSITIVE LOGITS
    âĵĺ
    0.94
    Dialogue
    0.87
    pmwiki
    0.81
    Trivia
    0.80
    Conclusion
    0.77
    reditary
    0.75
    Appearances
    0.74
    CONCLUS
    0.70
    Ü
    0.70
    Interview
    0.69
    Act Density 0.336%

    No Known Activations