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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     telefone
    -0.08
     compar
    -0.07
    lah
    -0.07
    学堂
    -0.07
     angry
    -0.07
    إمكان
    -0.07
    #aa
    -0.07
    واجب
    -0.06
    巴士
    -0.06
    (curl
    -0.06
    POSITIVE LOGITS
    0.07
    	F
    0.06
    ности
    0.06
    뵙
    0.06
    ┕
    0.06
    money
    0.06
    	raw
    0.06
    dict
    0.06
    -mort
    0.06
    瑖
    0.06
    Act Density 0.023%

    No Known Activations