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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    幖
    -0.08
     comfortably
    -0.07
    \db
    -0.07
     <--
    -0.07
    �
    -0.06
     מבין
    -0.06
    capture
    -0.06
    聞いた
    -0.06
    牝
    -0.06
    🎢
    -0.06
    POSITIVE LOGITS
     fraud
    0.07
     lantern
    0.07
    GER
    0.07
     Carlo
    0.07
     Maur
    0.07
    엄
    0.07
    rett
    0.07
    综合治理
    0.07
    BV
    0.07
    苞
    0.07
    Act Density 0.003%

    No Known Activations