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

    Neuronpedia

    INDEX
    Explanations

    references to academic research studies and findings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     chré
    -0.73
     eiffel
    -0.69
     Vaugh
    -0.66
     tricot
    -0.64
     religieuses
    -0.64
     spirituale
    -0.64
     eccl
    -0.63
     cristi
    -0.63
     veneta
    -0.63
     umbro
    -0.62
    POSITIVE LOGITS
     studies
    0.76
     evidence
    0.70
     research
    0.68
    studies
    0.63
    evidence
    0.59
     researched
    0.59
     Studies
    0.58
     scientifically
    0.56
     study
    0.55
    research
    0.54
    Act Density 0.317%

    No Known Activations