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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    thren
    -0.14
    (CG
    -0.14
    licted
    -0.14
     ActionTypes
    -0.14
    à¥Īद
    -0.13
    otton
    -0.13
    hte
    -0.13
    ément
    -0.13
    Nm
    -0.13
    (SK
    -0.13
    POSITIVE LOGITS
     everything
    0.16
    vip
    0.15
    éĢ£
    0.15
     linear
    0.15
    äs
    0.14
    ä¼¼
    0.14
    linear
    0.14
     everybody
    0.14
    аÑĪ
    0.14
    911
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.