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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     TRAIN
    -0.09
     Eisen
    -0.07
    ):
↵
    -0.07
     instr
    -0.07
    שירות
    -0.07
    .Sub
    -0.07
    Being
    -0.07
     GB
    -0.07
    别墅
    -0.06
    .host
    -0.06
    POSITIVE LOGITS
    .prop
    0.07
    ripsi
    0.07
    statuses
    0.07
    رابط
    0.06
     phé
    0.06
     lov
    0.06
    .paused
    0.06
    -checked
    0.06
     pouvez
    0.06
    rolls
    0.06
    Act Density 0.114%

    No Known Activations