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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sufficiency
    1.48
    sü
    1.48
    ों
    1.46
    માં
    1.42
     beginners
    1.38
     podľa
    1.37
    s
    1.37
    ുന്ന
    1.33
    ے
    1.33
    sı
    1.31
    POSITIVE LOGITS
     Chicks
    1.66
    ंस
    1.65
     Polarization
    1.58
    ist
    1.57
    阚
    1.50
    它可以
    1.49
     nhắn
    1.49
    ल
    1.49
    เตอร์
    1.45
    फॉ
    1.45
    Act Density 0.037%

    No Known Activations