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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ::_
    -0.08
    낯
    -0.07
    �
    -0.07
    త
    -0.07
    🔤
    -0.07
    .BufferedReader
    -0.07
     Hogwarts
    -0.07
    ประสบ
    -0.07
    ㅔ
    -0.07
    江北
    -0.07
    POSITIVE LOGITS
    =h
    0.09
     inherent
    0.08
    "L
    0.07
    ﲻ
    0.07
     designated
    0.07
    como
    0.07
    :+
    0.07
     COLUMN
    0.07
     engines
    0.06
    掌声
    0.06
    Act Density 0.007%

    No Known Activations