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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ans
    -0.08
     Chan
    -0.08
    ⓔ
    -0.08
    out
    -0.07
    ёт
    -0.07
    唐
    -0.07
    знач
    -0.07
     OM
    -0.07
    PART
    -0.07
     Instructor
    -0.07
    POSITIVE LOGITS
    盱
    0.08
    .qml
    0.07
     arrog
    0.07
     płyn
    0.07
    ﷲ
    0.06
     útil
    0.06
    客气
    0.06
    spiracy
    0.06
     scams
    0.06
    ȱ
    0.06
    Act Density 0.001%

    No Known Activations