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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     chees
    -0.07
    ems
    -0.07
     DE
    -0.07
     baked
    -0.07
     virtue
    -0.07
    -de
    -0.07
    ParseException
    -0.06
    凯
    -0.06
    _val
    -0.06
     verr
    -0.06
    POSITIVE LOGITS
    (:,:,
    0.08
    ⋋
    0.07
    相干
    0.07
    余额
    0.07
    osomal
    0.06
     =================================================================================
    0.06
    멩
    0.06
    ᔕ
    0.06
     getline
    0.06
    🔀
    0.06
    Act Density 0.001%

    No Known Activations