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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    2
    1.54
    ;
    1.49
    (
    1.30
    A
    1.25
    the
    1.23
    ↵↵
    1.16
    )
    1.03
    3
    1.02
    int
    0.95
    b
    0.95
    POSITIVE LOGITS
    ли
    1.43
    у
    1.20
    ية
    1.18
    larının
    1.16
    я
    1.14
    ৬
    1.14
    ৯
    1.13
    𝘀
    1.12
    لی
    1.10
    lerinin
    1.09
    Act Density 0.000%

    No Known Activations