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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific jargon

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marketplace
    -0.77
    ortium
    -0.72
    osponsors
    -0.70
     outright
    -0.69
     Oversight
    -0.66
     Infrastructure
    -0.66
    region
    -0.63
     CRC
    -0.63
     redes
    -0.61
     Nadu
    -0.60
    POSITIVE LOGITS
    xual
    1.01
     mund
    0.77
     charm
    0.75
     instincts
    0.72
     instinct
    0.72
     disson
    0.70
     carbs
    0.68
     throb
    0.68
    fuck
    0.68
     glasses
    0.68
    Act Density 0.678%

    No Known Activations