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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (regex
    -0.07
    jection
    -0.07
    flex
    -0.07
    一律
    -0.06
     Hiro
    -0.06
    냑
    -0.06
     proximity
    -0.06
     Mim
    -0.06
    conciliation
    -0.06
    angement
    -0.06
    POSITIVE LOGITS
    important
    0.08
     PHONE
    0.07
     Imp
    0.07
     Possibly
    0.07
     seperate
    0.07
     конкур
    0.07
    HomeController
    0.07
    节能减排
    0.07
     lear
    0.07
     scraper
    0.07
    Act Density 0.025%

    No Known Activations