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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     politicians
    -0.07
     interviews
    -0.07
    enable
    -0.07
     favourites
    -0.07
    敌
    -0.07
    discussion
    -0.07
     Autos
    -0.07
    …)
    -0.06
     moveTo
    -0.06
     Application
    -0.06
    POSITIVE LOGITS
    不少于
    0.07
     arsenal
    0.07
    Multiply
    0.07
    丧失
    0.07
    星空
    0.07
     fused
    0.06
     spoiled
    0.06
     witty
    0.06
    abra
    0.06
     Sidd
    0.06
    Act Density 0.019%

    No Known Activations