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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     layered
    0.75
    ែល
    0.72
     mudanças
    0.71
     verbeter
    0.71
     限定
    0.70
    ارهای
    0.68
     reformed
    0.67
    uriken
    0.67
    铉
    0.67
     cambiado
    0.67
    POSITIVE LOGITS
     aiding
    1.25
     knowingly
    1.21
     assisting
    1.20
     facilitating
    1.09
    协助
    1.06
     willfully
    1.04
     wilfully
    1.02
    facilit
    1.02
     disobey
    1.00
     assist
    1.00
    Act Density 0.768%

    No Known Activations