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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    延安
    -0.08
     sing
    -0.07
    膛
    -0.07
     zarówn
    -0.07
    	code
    -0.07
    -Americ
    -0.07
    넑
    -0.07
     insign
    -0.07
     brethren
    -0.07
    (test
    -0.07
    POSITIVE LOGITS
    ᴢ
    0.08
    遇到
    0.07
    dz
    0.07
     Up
    0.07
    								↵
    0.07
    ध
    0.07
     Pew
    0.07
    wow
    0.07
    Managed
    0.07
    ਪ
    0.07
    Act Density 0.016%

    No Known Activations