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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     czyli
    0.51
    及び
    0.51
    ])
    0.50
     및
    0.49
    .‏
    0.49
    یف
    0.48
     semblance
    0.47
    ायती
    0.46
     całość
    0.46
    ]。
    0.46
    POSITIVE LOGITS
    A
    0.47
     great
    0.46
    tout
    0.43
    No
    0.42
    s
    0.42
    Ne
    0.42
    New
    0.41
     aider
    0.40
    requests
    0.40
     কাছে
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.