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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Poetry
    -0.07
    ,password
    -0.07
     Provides
    -0.07
    俙
    -0.07
    --------------------
    -0.07
     beside
    -0.07
     viz
    -0.06
     aside
    -0.06
     heritage
    -0.06
     avoid
    -0.06
    POSITIVE LOGITS
    被淘汰
    0.07
     להמשיך
    0.07
    قرأ
    0.07
    留守
    0.07
    ℜ
    0.07
    rnd
    0.07
    lesen
    0.07
     قائلا
    0.07
     repeated
    0.06
    exam
    0.06
    Act Density 0.017%

    No Known Activations