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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    antro
    -0.29
    貧
    -0.28
    åįij
    -0.27
    ç´¯äºĨ
    -0.26
    licate
    -0.26
    裹
    -0.25
    æĪĸå¤ļ
    -0.25
    .writer
    -0.24
    Des
    -0.24
    ivity
    -0.24
    POSITIVE LOGITS
    æĭ¨
    0.32
    åºĦ
    0.31
     stere
    0.28
     cant
    0.27
     pipeline
    0.26
    ħ§
    0.25
    æĭĶ
    0.25
    oped
    0.25
    ç¼µ
    0.25
    å°±ä¸įèĥ½
    0.25
    Act Density 0.016%

    No Known Activations

    This feature has no known activations.