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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <bos>
    -0.65
     iscri
    -0.39
    tire
    -0.39
     démocratie
    -0.38
    outheast
    -0.37
    rise
    -0.37
     démoc
    -0.37
    ky
    -0.37
    SystemColors
    -0.36
     ainfi
    -0.36
    POSITIVE LOGITS
     was
    1.10
    was
    0.94
     were
    0.90
    Was
    0.85
     Was
    0.84
    were
    0.84
     WAS
    0.80
     было
    0.79
     WERE
    0.79
    Twas
    0.77
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.