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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    etre
    -0.07
    aton
    -0.07
    uum
    -0.06
    ביב
    -0.06
    慈
    -0.06
     Json
    -0.06
    trl
    -0.06
    管局
    -0.06
    燎
    -0.06
    冬
    -0.06
    POSITIVE LOGITS
     quien
    0.08
    (fe
    0.07
     stunned
    0.07
     learner
    0.07
     diploma
    0.07
     pronunciation
    0.07
     suprem
    0.07
    СП
    0.07
    が
    0.07
    -carousel
    0.07
    Act Density 0.024%

    No Known Activations