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
    temp
    -0.06
     witnessed
    -0.06
    ‵
    -0.06
     Gael
    -0.06
    gress
    -0.06
    Origin
    -0.06
    ل
    -0.06
    _gas
    -0.06
    Sc
    -0.06
    POSITIVE LOGITS
    很不错
    0.08
    bcm
    0.08
    的最佳
    0.07
    瘭
    0.07
    atorium
    0.07
     пара
    0.07
    遥远
    0.07
    ༄
    0.07
     Moreover
    0.06
    喳
    0.06
    Act Density 0.031%

    No Known Activations