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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (min
    -0.07
    𝚍
    -0.07
    (Stream
    -0.07
    �
    -0.06
     weighed
    -0.06
     incarnation
    -0.06
    _USERNAME
    -0.06
    ך
    -0.06
     Knowledge
    -0.06
    (max
    -0.06
    POSITIVE LOGITS
    情報
    0.08
     warming
    0.07
     CLOSED
    0.07
    agy
    0.07
     anzeigen
    0.07
     poj
    0.07
     Raised
    0.07
     defiant
    0.07
     baskı
    0.07
    颟
    0.07
    Act Density 0.002%

    No Known Activations