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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .nb
    -0.07
     Э
    -0.07
    邬
    -0.07
    出現
    -0.07
    ustom
    -0.07
     �
    -0.07
    峡谷
    -0.07
     Salv
    -0.07
    濒
    -0.07
    心理
    -0.06
    POSITIVE LOGITS
     digestion
    0.07
    methodName
    0.07
    相对于
    0.07
    괭
    0.07
     dishwasher
    0.07
    water
    0.07
     bulld
    0.07
     butterknife
    0.07
     WHITE
    0.07
    معاي
    0.07
    Act Density 0.004%

    No Known Activations