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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     -
    -0.22
     --
    -0.20
    ~
    -0.18
     '
    -0.18
     ...
    -0.17
     ('
    -0.17
     ("
    -0.17
    ...
    -0.16
    --
    -0.16
     ↵
    -0.15
    POSITIVE LOGITS
    wik
    0.15
     Facts
    0.15
    ousse
    0.14
    ãĥ¼ãĥ¬
    0.14
     facts
    0.14
    facts
    0.13
    LineWidth
    0.13
    reader
    0.13
    ]=$
    0.13
    _Application
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.