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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     appropriate
    0.48
     widely
    0.46
     diversified
    0.46
     preferred
    0.45
     widespread
    0.45
     accurate
    0.44
     adecuado
    0.44
    accurate
    0.44
     antiguo
    0.44
     natural
    0.43
    POSITIVE LOGITS
    哪些
    0.60
     якія
    0.53
     которые
    0.52
    дные
    0.52
    которые
    0.47
     които
    0.46
     lesquels
    0.46
    лых
    0.45
     jotka
    0.44
    лые
    0.42
    Act Density 0.011%

    No Known Activations