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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     replacing
    -0.09
     cine
    -0.07
    esy
    -0.07
     전혀
    -0.06
    .Inject
    -0.06
    幅
    -0.06
     debate
    -0.06
    ']
↵
↵
    -0.06
     espan
    -0.06
    OMEM
    -0.06
    POSITIVE LOGITS
    走了
    0.07
     (£
    0.07
     düzey
    0.07
     двигател
    0.07
     rhythms
    0.07
    (rules
    0.07
    Generator
    0.07
     DISTRIBUT
    0.07
    checker
    0.07
    .fac
    0.07
    Act Density 0.007%

    No Known Activations