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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     küçük
    -0.08
    	cc
    -0.07
    erte
    -0.07
     World
    -0.07
    预警
    -0.07
    奖励
    -0.07
    جريدة
    -0.07
     Eug
    -0.07
    etre
    -0.06
    这几
    -0.06
    POSITIVE LOGITS
     husband
    0.08
     mach
    0.08
    吱
    0.07
    HSV
    0.07
     chồng
    0.07
    U
    0.07
    Armor
    0.07
    COMP
    0.07
    Usage
    0.07
    ESP
    0.07
    Act Density 0.009%

    No Known Activations