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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𫐄
    -0.08
    .vocab
    -0.08
     Valve
    -0.07
    avra
    -0.07
    ﭭ
    -0.07
    _dev
    -0.07
    ﭫ
    -0.07
     tendon
    -0.07
    _invoice
    -0.07
     Julie
    -0.06
    POSITIVE LOGITS
    ערה
    0.07
     Mer
    0.07
     请求
    0.07
     Works
    0.06
     ---
    0.06
    会谈
    0.06
    篁
    0.06
    ?('
    0.06
    …………
    0.06
    زر
    0.06
    Act Density 0.050%

    No Known Activations