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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     spiele
    -0.07
    쩝
    -0.07
     Fluid
    -0.07
     מאוד
    -0.07
    否
    -0.07
     Salon
    -0.06
    bar
    -0.06
     levels
    -0.06
     grinder
    -0.06
     blended
    -0.06
    POSITIVE LOGITS
    urgence
    0.07
    -stat
    0.07
    xxxxxxxx
    0.07
    ńst
    0.07
    \">"
    0.07
     Employment
    0.07
    isper
    0.07
    她是
    0.07
    oded
    0.07
    就得
    0.07
    Act Density 0.006%

    No Known Activations