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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0.44
    -
    0.40
    eli
    0.40
    .
    0.40
    ación
    0.39
     in
    0.38
    кі
    0.38
    liste
    0.37
    لی
    0.36
    lan
    0.36
    POSITIVE LOGITS
    ות
    0.51
     jazy
    0.48
    W
    0.47
    ون
    0.46
    T
    0.45
    ８
    0.43
     stá
    0.41
    X
    0.41
    多么
    0.40
    O
    0.39
    Act Density 3.546%

    No Known Activations