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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     trivia
    -0.09
    _Word
    -0.08
    免税
    -0.07
     dint
    -0.07
    ritch
    -0.07
     iota
    -0.07
    Forest
    -0.07
    avar
    -0.07
     villa
    -0.07
     Furniture
    -0.07
    POSITIVE LOGITS
    0.08
     theoretical
    0.07
     Dev
    0.07
    *
    0.07
    \\\
    0.07
    OP
    0.06
    ?>">↵
    0.06
    そこに
    0.06
     Breaking
    0.06
    .ttf
    0.06
    Act Density 0.002%

    No Known Activations