INDEX
    Explanations

    This neuron detects mentions of the Jainism religion (tokens like “Jain” and “ism”).

    New Auto-Interp
    Negative Logits
     лечение
    -0.07
    -0.07
    .Publish
    -0.06
    skyt
    -0.06
    attributes
    -0.06
    -0.06
     длин
    -0.06
    ()
    ↵
    ↵
    ↵
    -0.06
     violated
    -0.06
    -0.06
    POSITIVE LOGITS
    cmpeq
    0.07
     Raymond
    0.06
     Lotus
    0.06
    brand
    0.06
    ham
    0.06
    аков
    0.06
    iteDatabase
    0.06
    、三
    0.06
    +B
    0.06
     Hose
    0.06
    Act Density 0.002%

    No Known Activations