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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     analyze
    -0.09
    حد
    -0.07
    单项
    -0.07
    aven
    -0.07
     uten
    -0.07
    ⾳
    -0.07
    _rnn
    -0.07
    óst
    -0.06
     "\"
    -0.06
    纵向
    -0.06
    POSITIVE LOGITS
    centage
    0.07
     cats
    0.07
    .Information
    0.06
    자는
    0.06
     Life
    0.06
    踩
    0.06
    .left
    0.06
     wsz
    0.06
     התורה
    0.06
    riends
    0.06
    Act Density 0.025%

    No Known Activations