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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cogn
    -0.08
    💰
    -0.07
    efe
    -0.07
     gaze
    -0.07
    ureka
    -0.07
     thừa
    -0.07
    _outputs
    -0.07
     sushi
    -0.07
     Dirt
    -0.07
    Developer
    -0.06
    POSITIVE LOGITS
     הפי
    0.07
    𝗳
    0.07
    パターン
    0.06
    פיד
    0.06
     pakistan
    0.06
    녤
    0.06
    <bits
    0.06
     having
    0.06
    څ
    0.06
    院
    0.06
    Act Density 0.009%

    No Known Activations