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

    Neuronpedia

    INDEX
    Explanations

    file download related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    abetes
    -0.60
     فريبيس
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    Abbiamo
    -0.55
     سكانية
    -0.54
     turi
    -0.54
    Được
    -0.53
    новниш
    -0.53
     cajones
    -0.53
    хьтан
    -0.52
    POSITIVE LOGITS
     embodi
    1.09
     lola
    0.93
     contex
    0.91
     starbucks
    0.89
     panama
    0.88
     lts
    0.88
     sophie
    0.87
     ACKNOWLEDGMENTS
    0.87
    TheGreat
    0.86
     tiffany
    0.86
    Act Density 0.173%

    No Known Activations