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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    真相
    -0.08
    ception
    -0.08
    藟
    -0.07
    uffy
    -0.07
    .getSeconds
    -0.07
     solicit
    -0.07
    want
    -0.07
     Further
    -0.07
     dit
    -0.07
    antage
    -0.07
    POSITIVE LOGITS
     artist
    0.07
    环比
    0.07
    厍
    0.07
     rugs
    0.07
    🎉
    0.07
     strong
    0.06
    تكن
    0.06
    𝐱
    0.06
     poet
    0.06
    amat
    0.06
    Act Density 0.001%

    No Known Activations