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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    タル
    -0.08
    yar
    -0.07
     slate
    -0.07
    ávě
    -0.06
     bestowed
    -0.06
     Seks
    -0.06
    ��
    -0.06
     difer
    -0.06
     getir
    -0.06
    (pdev
    -0.06
    POSITIVE LOGITS
    things
    0.06
     Announcement
    0.06
    intent
    0.06
    所以
    0.06
     Burke
    0.06
    окс
    0.06
     directly
    0.06
     RB
    0.06
     रखत
    0.06
    gens
    0.06
    Act Density 0.001%

    No Known Activations