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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    +.
    1.45
    。
    1.38
    .
    1.34
    ".
    1.30
    ।
    1.27
    %.
    1.25
    ."
    1.24
    !.
    1.21
    '.
    1.20
    .).
    1.19
    POSITIVE LOGITS
    **,
    1.58
    [],
    1.46
    ,",
    1.45
    ,$$
    1.44
    ₂,
    1.44
    *,
    1.43
    ,*
    1.39
     [],
    1.37
    (),
    1.37
    ],
    1.36
    Act Density 3.186%

    No Known Activations