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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    上次
    -0.08
     внимание
    -0.08
    جائزة
    -0.07
     يوس
    -0.07
    ご
    -0.07
    in
    -0.07
    룀
    -0.07
    不管你
    -0.06
    仅仅是
    -0.06
    iku
    -0.06
    POSITIVE LOGITS
    bred
    0.07
    厨师
    0.07
     besie
    0.07
     sprink
    0.06
     Patri
    0.06
    🐩
    0.06
     Kab
    0.06
    ailer
    0.06
     Picker
    0.06
    设备
    0.06
    Act Density 0.023%

    No Known Activations