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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    excerpt
    -0.08
    책
    -0.08
     tribute
    -0.08
    不明
    -0.08
    מוג
    -0.08
     article
    -0.07
     Service
    -0.07
    _ATTRIBUTE
    -0.07
    💗
    -0.07
    ﰌ
    -0.07
    POSITIVE LOGITS
     di
    0.08
     Они
    0.07
     تقوم
    0.07
    ,Y
    0.07
    _call
    0.07
    иков
    0.07
    izia
    0.07
    ilty
    0.07
    ,+
    0.07
    込
    0.07
    Act Density 0.027%

    No Known Activations