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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ouk
    0.39
    标注
    0.37
    omey
    0.36
    جس
    0.35
    驗
    0.35
    ੇ
    0.35
    諭
    0.35
    eluk
    0.35
     অনুষ্ঠ
    0.34
    が増
    0.34
    POSITIVE LOGITS
     evapor
    0.44
    畿
    0.41
     diamonds
    0.40
    𝔹
    0.40
     tornadoes
    0.40
     Hardin
    0.39
    Cincinnati
    0.39
     murdered
    0.38
    cipl
    0.38
    observe
    0.38
    Act Density 0.001%

    No Known Activations