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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     קצר
    -0.08
     חוב
    -0.07
    舍不得
    -0.07
    暫
    -0.07
     Bits
    -0.07
    ญา
    -0.07
     resistance
    -0.07
     כסף
    -0.07
     девуш
    -0.06
     sé
    -0.06
    POSITIVE LOGITS
    nych
    0.07
    couldn
    0.07
    jectory
    0.07
    꾜
    0.07
     make
    0.07
    printed
    0.07
     chemin
    0.07
     coop
    0.07
    shadow
    0.07
     sources
    0.07
    Act Density 0.020%

    No Known Activations