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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    �
    -0.07
    وري
    -0.07
     béné
    -0.07
    感觉
    -0.07
     تن
    -0.06
    🦋
    -0.06
    茽
    -0.06
     đào
    -0.06
    Imagen
    -0.06
    쳇
    -0.06
    POSITIVE LOGITS
     invokes
    0.07
    thew
    0.07
     leak
    0.07
    錯
    0.07
     jedną
    0.07
     leaked
    0.07
     startX
    0.07
     smells
    0.07
    (handler
    0.07
     impulses
    0.07
    Act Density 0.004%

    No Known Activations