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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ware
    -0.29
     Compression
    -0.27
    Compression
    -0.27
     compression
    -0.26
    erp
    -0.26
    lod
    -0.26
    ier
    -0.26
    brush
    -0.25
    .Controllers
    -0.24
    çªģçł´åı£
    -0.24
    POSITIVE LOGITS
    趣
    0.28
    åıijçĶŁäºĨ
    0.28
    quia
    0.27
    欲
    0.27
    iej
    0.26
    .trailing
    0.26
    çķ¥
    0.26
     gamb
    0.26
    æĥ³
    0.26
    stead
    0.25
    Act Density 0.838%

    No Known Activations

    This feature has no known activations.