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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Employee
    -0.07
     Pixel
    -0.07
    School
    -0.07
    Internal
    -0.07
    英特尔
    -0.07
    �
    -0.07
     Emergency
    -0.06
    iny
    -0.06
    iry
    -0.06
    .players
    -0.06
    POSITIVE LOGITS
    恐怖
    0.07
     gravitational
    0.07
    بدا
    0.07
    穿衣
    0.07
    苎
    0.07
     נהדר
    0.06
     bat
    0.06
    足以
    0.06
    ᴖ
    0.06
    ⽬
    0.06
    Act Density 0.327%

    No Known Activations