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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     segi
    0.88
    ed
    0.86
     cele
    0.79
    <0x0D>
    0.77
    Mix
    0.76
    不说
    0.73
    a
    0.73
    los
    0.72
     사
    0.72
     tidak
    0.72
    POSITIVE LOGITS
    <unused2190>
    0.93
     thereby
    0.93
     repeatedly
    0.92
     frantically
    0.89
     bahsed
    0.89
    \%.
    0.89
     terrified
    0.87
     collaboratively
    0.85
    consulté
    0.85
    ließend
    0.84
    Act Density 0.611%

    No Known Activations