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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	panic
    -0.08
    	dist
    -0.07
     FUCK
    -0.07
     lymph
    -0.07
     Temple
    -0.07
     ABI
    -0.07
    拜师
    -0.07
     transplant
    -0.07
    [arg
    -0.06
     metast
    -0.06
    POSITIVE LOGITS
    例えば
    0.07
     loyalty
    0.07
    relationships
    0.07
    ,cljs
    0.07
    であろう
    0.07
     العلاقات
    0.06
    ราม
    0.06
     jylland
    0.06
    六个
    0.06
    horia
    0.06
    Act Density 0.000%

    No Known Activations