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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sounding
    -0.07
    leurs
    -0.07
    Unavailable
    -0.07
     valido
    -0.07
    おかげ
    -0.07
    짓
    -0.07
     Caleb
    -0.07
     Auth
    -0.07
     ساع
    -0.06
     dile
    -0.06
    POSITIVE LOGITS
     Thousand
    0.08
     //////////////////
    0.08
    iei
    0.08
     предприятия
    0.07
    🧗
    0.07
    请你
    0.07
     __________________
    0.07
    岸边
    0.07
    <b
    0.07
    当之
    0.07
    Act Density 0.039%

    No Known Activations