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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    /
    0.61
     (
    0.55
     /
    0.54
     =
    0.54
     -
    0.52
     ('
    0.50
     '
    0.49
     (=
    0.49
    0.48
     or
    0.47
    POSITIVE LOGITS
    said
    0.79
     dijo
    0.77
     తెలిపారు
    0.75
     spokeswoman
    0.73
    说道
    0.71
     сказал
    0.71
     spokesperson
    0.70
     afirmou
    0.70
     spokesman
    0.70
     ಹೇಳಿದರು
    0.69
    Act Density 0.001%

    No Known Activations