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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     แต่
    0.49
     However
    0.45
     pero
    0.44
    하지만
    0.44
    etc
    0.43
     and
    0.42
    However
    0.42
    지만
    0.40
     하지만
    0.40
     Etc
    0.40
    POSITIVE LOGITS
     subsequently
    0.96
     consequently
    0.86
     thus
    0.84
     ultimately
    0.79
     thereby
    0.78
     possibly
    0.77
     potentially
    0.76
     therefore
    0.75
     hence
    0.73
    因此
    0.66
    Act Density 1.033%

    No Known Activations