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

    Neuronpedia

    INDEX
    Explanations

    commands and steps related to setting up and using software or technical tools

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fta
    -1.21
     ftu
    -1.11
     bourgeo
    -1.11
     increa
    -1.10
     fte
    -1.09
     alre
    -1.08
     quitted
    -1.08
     suscep
    -1.07
     intermitt
    -1.06
     bordeaux
    -1.05
    POSITIVE LOGITS
     develop
    0.83
     create
    0.81
     design
    0.80
     designing
    0.80
    <bos>
    0.75
     construct
    0.75
     build
    0.75
     creation
    0.74
     created
    0.73
     creating
    0.72
    Act Density 0.589%

    No Known Activations