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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Acting
    0.53
    Search
    0.52
     Acting
    0.51
     acting
    0.50
    gin
    0.48
    dem
    0.48
    Dem
    0.47
    ne
    0.46
    in
    0.46
    ]."
    0.45
    POSITIVE LOGITS
    ྪ
    0.63
     debounce
    0.57
    ྥ
    0.55
    δρο
    0.52
    ྵ
    0.52
    Ꮼ
    0.52
    డం
    0.51
    咘
    0.51
    ảm
    0.50
     таблицы
    0.50
    Act Density 0.000%

    No Known Activations