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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Zhang
    -0.07
    Mask
    -0.07
     Smart
    -0.07
    cond
    -0.07
     alignment
    -0.06
     involves
    -0.06
     قادر
    -0.06
    .row
    -0.06
     survival
    -0.06
     Comparison
    -0.06
    POSITIVE LOGITS
     feu
    0.08
    ORIZ
    0.07
    我去
    0.07
    书院
    0.07
    说我
    0.07
    CppMethodInitialized
    0.07
     architect
    0.07
     büyü
    0.07
    probably
    0.07
    tempts
    0.07
    Act Density 0.027%

    No Known Activations