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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (g
    -0.07
    inf
    -0.07
     Klaus
    -0.06
     dre
    -0.06
    们都
    -0.06
     princip
    -0.06
     minors
    -0.06
    (v
    -0.06
     larg
    -0.06
    gregar
    -0.06
    POSITIVE LOGITS
     ceremony
    0.08
    אנגלית
    0.08
    งาน
    0.07
     Atatürk
    0.07
     nonatomic
    0.07
     orgas
    0.07
    Hello
    0.07
    .Word
    0.07
    jectory
    0.07
    走廊
    0.07
    Act Density 0.053%

    No Known Activations