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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (
    0.62
    0.51
     harsh
    0.50
     wild
    0.49
     I
    0.49
     Wildlife
    0.48
     Sky
    0.46
     absurdity
    0.46
     high
    0.45
    ---
    0.45
    POSITIVE LOGITS
     Mesmo
    0.63
     сына
    0.57
    лянчук
    0.52
    兒子
    0.52
     обучения
    0.51
     erneut
    0.51
    mdui
    0.51
    鄔
    0.50
    飡
    0.49
     encontrado
    0.49
    Act Density 0.001%

    No Known Activations