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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ۹
    1.45
    ۵
    1.25
    א
    1.23
    та
    1.18
    )।
    1.17
    ی
    1.16
    ।’
    1.13
    ری
    1.09
    "।
    1.09
     an
    1.09
    POSITIVE LOGITS
    u
    1.97
    er
    1.70
    e
    1.48
    ur
    1.46
    ed
    1.42
    o
    1.40
    ul
    1.35
    .
    1.32
    og
    1.29
    n
    1.27
    Act Density 0.000%

    No Known Activations