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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    although
    0.80
    Therefore
    0.76
    though
    0.75
     dunque
    0.73
     поэтому
    0.72
    Although
    0.70
     nhưng
    0.70
    Aunque
    0.70
    aunque
    0.70
    Though
    0.69
    POSITIVE LOGITS
    也要
    0.64
    也将
    0.64
     także
    0.62
    只限
    0.61
     also
    0.61
     पनि
    0.58
    同時に
    0.58
     आल्सो
    0.58
    要注意
    0.57
    他也
    0.57
    Act Density 0.322%

    No Known Activations