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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Var
    -0.07
     students
    -0.07
    consum
    -0.07
     leaders
    -0.07
    难得
    -0.07
    被告
    -0.07
    🆙
    -0.07
     nadzie
    -0.07
    ().
    -0.07
    证监会
    -0.07
    POSITIVE LOGITS
    YY
    0.08
     Lily
    0.07
    aad
    0.07
    烏
    0.07
     registering
    0.07
    ᵞ
    0.07
    حط
    0.07
     wiping
    0.07
    atican
    0.07
     snapping
    0.07
    Act Density 0.003%

    No Known Activations