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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     seiz
    -0.78
    PIN
    -0.72
    rouse
    -0.69
    hent
    -0.69
    %]
    -0.68
     Debor
    -0.67
    sold
    -0.67
    icides
    -0.67
    vati
    -0.67
     bonds
    -0.66
    POSITIVE LOGITS
     Socket
    0.67
    ModLoader
    0.64
    liest
    0.62
     RW
    0.62
     Garrison
    0.62
     Standing
    0.61
    ozy
    0.61
     Canal
    0.61
     Armory
    0.59
     FN
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.