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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ится
    -0.09
     vested
    -0.07
    👵
    -0.07
     restless
    -0.07
     sleepy
    -0.07
     trustworthy
    -0.07
     сит
    -0.06
    胆固
    -0.06
    illian
    -0.06
     getch
    -0.06
    POSITIVE LOGITS
    Bi
    0.08
    𝛾
    0.07
    loi
    0.07
    ówn
    0.07
    solver
    0.06
     Log
    0.06
    雞
    0.06
    ghi
    0.06
     NOTICE
    0.06
    卻
    0.06
    Act Density 0.171%

    No Known Activations