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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    species
    -0.07
     begin
    -0.07
     Restricted
    -0.07
    暇
    -0.07
    Overview
    -0.06
    极大
    -0.06
    arker
    -0.06
     pork
    -0.06
    𝙺
    -0.06
    -mar
    -0.06
    POSITIVE LOGITS
    各行各业
    0.08
    ONES
    0.08
    同业
    0.07
     Essence
    0.07
    겠습니다
    0.07
    XYZ
    0.07
    .'↵↵
    0.07
    |RF
    0.07
    全过程
    0.06
    。",↵
    0.06
    Act Density 0.008%

    No Known Activations