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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     or
    0.62
     якобы
    0.62
     (
    0.61
    mentioned
    0.56
    提及
    0.54
     certain
    0.53
    ன்றும்
    0.52
    etc
    0.51
     mentioned
    0.50
    or
    0.50
    POSITIVE LOGITS
     başlayalım
    1.14
    ครับ
    1.11
     dunque
    1.03
     vamos
    1.02
    ！
    1.00
    <unused2190>
    0.99
     saya
    0.97
    ค่ะ
    0.97
     정리
    0.96
     continuamos
    0.95
    Act Density 4.085%

    No Known Activations