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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    سمع
    -0.08
    握住
    -0.07
     prepare
    -0.07
    王某
    -0.07
     charming
    -0.07
     Phillip
    -0.07
    赶上
    -0.07
    听到
    -0.07
     этим
    -0.07
     raspberry
    -0.07
    POSITIVE LOGITS
    揍
    0.08
    .optimize
    0.07
    clusive
    0.07
     violence
    0.07
    щ
    0.07
     brutality
    0.06
     infra
    0.06
     SO
    0.06
    ologie
    0.06
    сер
    0.06
    Act Density 0.010%

    No Known Activations