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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     living
    0.66
     Living
    0.57
    living
    0.54
     Live
    0.51
     LIVING
    0.50
    Living
    0.50
     live
    0.49
     жить
    0.49
    Live
    0.45
     живе
    0.45
    POSITIVE LOGITS
     attraverso
    0.46
     través
    0.44
     adquirido
    0.42
     theology
    0.41
     injustices
    0.40
     adquir
    0.40
    世界の
    0.40
     telas
    0.40
     неравен
    0.39
     batalla
    0.39
    Act Density 0.002%

    No Known Activations