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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    doms
    -0.74
    stood
    -0.73
    edin
    -0.73
    PsyNetMessage
    -0.71
     Babel
    -0.71
    Graph
    -0.69
    riers
    -0.69
     è£ıè
    -0.69
     Consumption
    -0.68
    Container
    -0.68
    POSITIVE LOGITS
     eleph
    0.86
     fug
    0.71
     coup
    0.68
    htaking
    0.67
     disarm
    0.67
     irresist
    0.66
     mag
    0.64
     tum
    0.63
     bald
    0.63
     restoration
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.