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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (guid
    -0.08
     conten
    -0.07
    displayName
    -0.07
    find
    -0.07
     Est
    -0.07
     characteristic
    -0.07
    powers
    -0.07
     Battles
    -0.07
    修正
    -0.07
     tử
    -0.07
    POSITIVE LOGITS
    _MY
    0.07
    ↵  ↵
    0.07
    (Socket
    0.06
    ài
    0.06
    两千
    0.06
    私人
    0.06
    _sym
    0.06
    🕝
    0.06
     יודעים
    0.06
    ина
    0.06
    Act Density 0.004%

    No Known Activations