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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     four
    0.61
    :
    0.52
     H
    0.48
    标准
    0.48
     ハ
    0.48
     S
    0.46
     three
    0.46
    选择了
    0.46
    H
    0.46
     acetic
    0.46
    POSITIVE LOGITS
     något
    0.61
     mutta
    0.60
     nhưng
    0.57
     pero
    0.57
     Nhưng
    0.57
     richtigen
    0.56
    🤧
    0.56
     terutama
    0.55
     soprattutto
    0.55
     너무
    0.55
    Act Density 0.327%

    No Known Activations