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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .concurrent
    -0.07
     Attempt
    -0.07
     Satan
    -0.07
     sudo
    -0.07
    .dot
    -0.07
     rode
    -0.07
    raj
    -0.07
    猱
    -0.06
    nown
    -0.06
     fasting
    -0.06
    POSITIVE LOGITS
     punctuation
    0.08
     justifyContent
    0.08
    "))
    0.08
     tweeted
    0.07
     molecule
    0.07
    ------+------+
    0.07
    站起来
    0.07
     Blick
    0.07
     Responsibilities
    0.07
    诠释
    0.07
    Act Density 0.002%

    No Known Activations