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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     σκο
    0.90
    <unused21>
    0.89
    <unused13>
    0.85
    <unused92>
    0.85
    ット
    0.85
    柯
    0.85
    amps
    0.84
    𝗼
    0.84
    ти
    0.82
    álen
    0.82
    POSITIVE LOGITS
     and
    1.15
    的一部分
    0.93
    그래서
    0.92
     whose
    0.89
     joten
    0.88
     for
    0.87
     యొక్క
    0.87
     पद्धतीने
    0.86
     salespeople
    0.86
     wasn
    0.86
    Act Density 1.142%

    No Known Activations