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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gossip
    0.69
     entire
    0.67
     VI
    0.65
     micro
    0.62
     ET
    0.61
     purification
    0.61
     pro
    0.59
     E
    0.59
     lig
    0.58
     lunar
    0.57
    POSITIVE LOGITS
    Inicial
    0.75
    pessoa
    0.67
    йтесь
    0.66
     socialists
    0.65
     最初
    0.64
    ilerden
    0.63
     θεω
    0.63
    pessoas
    0.62
    artista
    0.61
     insanların
    0.61
    Act Density 0.000%

    No Known Activations