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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     rugged
    0.71
     more
    0.64
     shared
    0.63
     kira
    0.61
     lean
    0.58
     fores
    0.58
     far
    0.57
     pruned
    0.57
     más
    0.57
     prefers
    0.56
    POSITIVE LOGITS
     然后
    0.76
     এরপর
    0.74
    その後
    0.74
     inital
    0.71
     После
    0.70
     然後
    0.69
    এরপর
    0.67
     試験
    0.66
    เริ่มต้น
    0.66
    当然
    0.65
    Act Density 0.000%

    No Known Activations