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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Camp
    -0.08
     thou
    -0.07
    肆
    -0.07
    atio
    -0.07
     dou
    -0.07
    opsis
    -0.07
     thumbs
    -0.06
     AES
    -0.06
    Ư
    -0.06
    拜
    -0.06
    POSITIVE LOGITS
    immutable
    0.08
     accessible
    0.07
    一边
    0.07
     är
    0.07
     Diary
    0.07
     perks
    0.07
     contribute
    0.07
     inertia
    0.07
     Learned
    0.07
    壓力
    0.07
    Act Density 0.001%

    No Known Activations