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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     A
    0.92
     G
    0.87
     ",
    0.82
     "
    0.79
     I
    0.79
     F
    0.77
     O
    0.76
     R
    0.75
     "")
    0.73
     “
    0.73
    POSITIVE LOGITS
     hectare
    0.86
    pig
    0.85
    hunger
    0.85
    꿩
    0.85
    樎
    0.84
    harmon
    0.83
     tetr
    0.82
    ствовали
    0.82
     buddhav
    0.81
    $^{
    0.81
    Act Density 0.000%

    No Known Activations