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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lyn
    -0.63
     concurrent
    -0.62
    £ı
    -0.61
     runaway
    -0.61
     Polaris
    -0.60
     PASS
    -0.60
    etheless
    -0.58
     Imaging
    -0.58
     hiber
    -0.58
     Morg
    -0.58
    POSITIVE LOGITS
    ienne
    0.80
     dab
    0.70
    utive
    0.70
    afe
    0.70
    ien
    0.68
    imus
    0.68
    ix
    0.66
    Override
    0.66
    atron
    0.66
    rag
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.