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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    тной
    1.29
    oirs
    1.24
     avanzando
    1.24
     ponctuées
    1.24
     sino
    1.22
    тным
    1.21
     laissent
    1.20
     llevó
    1.20
     caranya
    1.19
     tense
    1.19
    POSITIVE LOGITS
    S
    1.10
    Known
    1.06
    er
    1.05
     Loyal
    1.04
    hydraz
    1.03
     runat
    1.01
    D
    0.98
    P
    0.97
    I
    0.96
    hyd
    0.96
    Act Density 0.000%

    No Known Activations