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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    8
    -0.08
     chap
    -0.07
    ackson
    -0.07
    แมน
    -0.07
    Ι
    -0.07
    .swt
    -0.07
    ymmetric
    -0.07
     maple
    -0.07
     государ
    -0.06
    饽
    -0.06
    POSITIVE LOGITS
     כת
    0.08
     deny
    0.08
     �
    0.07
     ден
    0.07
    “We
    0.07
     denies
    0.07
     denied
    0.07
    田野
    0.07
    否认
    0.07
    _arg
    0.07
    Act Density 0.009%

    No Known Activations