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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    DATA
    0.43
    Stern
    0.41
    ̈
    0.40
     corpora
    0.39
     основе
    0.38
     "
    0.38
     οι
    0.38
    ********
    0.37
     pools
    0.37
    anej
    0.37
    POSITIVE LOGITS
     Juego
    0.53
     peut
    0.49
     câble
    0.49
     obice
    0.49
     esfuerzos
    0.48
     Espagne
    0.48
     tangente
    0.48
    それは
    0.48
     cible
    0.48
     cadeau
    0.47
    Act Density 0.004%

    No Known Activations