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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     »
    -0.19
     ãĢį
    -0.18
    &apos
    -0.17
     «
    -0.17
     »,
    -0.17
    âĢŀ
    -0.16
     âĢŀ
    -0.16
    apos
    -0.15
     ».
    -0.15
    "—
    -0.15
    POSITIVE LOGITS
    **
    0.29
    **↵
    0.26
     **
    0.24
    )**
    0.24
    ,**
    0.23
     **↵
    0.23
    :**
    0.23
    ~~
    0.23
    **(
    0.22
    ***↵
    0.22
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.