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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    choose
    -0.07
    抚
    -0.07
    .Sm
    -0.07
    锓
    -0.07
     MPs
    -0.07
    随便
    -0.07
    /helper
    -0.06
     remedy
    -0.06
     Kid
    -0.06
     Homeland
    -0.06
    POSITIVE LOGITS
     strategist
    0.08
    荮
    0.07
    伎
    0.07
     additives
    0.07
    glich
    0.07
    追求
    0.07
    תוצאה
    0.06
     pouco
    0.06
    担任
    0.06
    ionate
    0.06
    Act Density 0.021%

    No Known Activations