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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    の種類
    0.70
     hatred
    0.66
    ົາ
    0.64
     Правда
    0.62
     contrário
    0.61
     остальные
    0.61
     нельзя
    0.61
    あの
    0.61
     además
    0.60
    たくさんの
    0.60
    POSITIVE LOGITS
     thereafter
    0.74
     Throughout
    0.73
     Thereafter
    0.71
     onwards
    0.67
     throughout
    0.66
     posteriores
    0.66
     seguenti
    0.64
    수로
    0.64
     biennium
    0.62
     beyond
    0.61
    Act Density 0.000%

    No Known Activations