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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ve
    0.56
    ll
    0.53
    tense
    0.52
    0.52
     eukary
    0.52
     okazji
    0.52
    ⃘
    0.51
     snug
    0.50
    vaccinated
    0.50
    🤠
    0.49
    POSITIVE LOGITS
     জাহান
    0.46
    ೊ
    0.44
     cumpl
    0.42
    En
    0.42
    cento
    0.41
    ድ
    0.40
     प्रश
    0.40
    Twenty
    0.39
    首先
    0.38
     сверху
    0.38
    Act Density 0.002%

    No Known Activations