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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    愛情
    -0.07
     thư
    -0.07
    artisanlib
    -0.07
     sad
    -0.07
    زيد
    -0.07
    ﲨ
    -0.07
    魅力
    -0.07
     sû
    -0.07
    ار
    -0.07
    狂
    -0.07
    POSITIVE LOGITS
    각
    0.08
     각
    0.08
     distinctly
    0.07
     speak
    0.07
    舶
    0.07
     speaking
    0.07
    꿴
    0.07
     dialect
    0.07
    Χ
    0.07
    Speak
    0.07
    Act Density 0.046%

    No Known Activations