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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ikor
    0.40
    ट्टे
    0.38
     بڑ
    0.38
     যাই
    0.36
    은행
    0.36
     errado
    0.36
    NSError
    0.35
    antry
    0.35
     গোটা
    0.35
    芸
    0.35
    POSITIVE LOGITS
     Inference
    0.45
     適
    0.42
     inference
    0.41
     qualified
    0.41
     coordination
    0.41
     coordinador
    0.40
     designate
    0.40
     politič
    0.40
     koordin
    0.38
     inferences
    0.38
    Act Density 0.001%

    No Known Activations