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

    Neuronpedia

    INDEX
    Explanations

    titles and information related to research papers, articles, books, and academic publications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    azor
    -0.75
     curtains
    -0.74
    adra
    -0.71
    icably
    -0.69
     blaster
    -0.68
     unlucky
    -0.67
     fighters
    -0.67
     cooler
    -0.66
     fridge
    -0.65
     dough
    -0.64
    POSITIVE LOGITS
     Retrieved
    1.27
     Proceedings
    1.15
     Edited
    1.06
    published
    1.00
     Handbook
    0.99
     Perspect
    0.97
     Princeton
    0.96
     Journal
    0.95
     reprinted
    0.93
     pp
    0.92
    Act Density 0.434%

    No Known Activations