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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     daž
    1.05
     worm
    0.92
     dokt
    0.91
    punt
    0.91
     tránh
    0.91
     rappelle
    0.91
     corruption
    0.90
     relapse
    0.89
    airobi
    0.88
    élène
    0.88
    POSITIVE LOGITS
    Т
    1.11
    Vý
    1.07
    𝙋
    1.06
    Nome
    1.04
    वंत
    1.01
     Vý
    1.01
    Ρ
    1.01
     Whatever
    1.00
    Questa
    0.96
    Whatever
    0.93
    Act Density 0.000%

    No Known Activations