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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     again
    0.76
     wish
    0.75
    ...
    0.75
     up
    0.73
     =
    0.72
    !
    0.72
    :
    0.70
     on
    0.69
     would
    0.66
    0.66
    POSITIVE LOGITS
     Первая
    0.81
     Podczas
    0.81
     Eigenschaften
    0.80
     Wanneer
    0.78
     tuttavia
    0.78
     Asimismo
    0.78
    pubescens
    0.77
     kammam
    0.76
     Međutim
    0.76
    Asimismo
    0.75
    Act Density 0.000%

    No Known Activations