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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     repl
    0.92
     disc
    0.92
     bleached
    0.91
     discs
    0.91
     re
    0.91
     swapped
    0.89
     swap
    0.88
     tiles
    0.87
     mul
    0.87
     nudge
    0.86
    POSITIVE LOGITS
    م
    1.21
    Griff
    1.04
    री
    1.04
    ⿹
    1.03
    So
    1.01
    Critical
    0.99
    न
    0.98
    Pregnant
    0.97
    amilton
    0.94
    Ze
    0.94
    Act Density 0.000%

    No Known Activations