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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    in
    1.61
    er
    1.46
    f
    1.29
    ین
    1.28
    ش
    1.27
    ut
    1.27
    ח
    1.27
    ف
    1.20
    ہ
    1.16
    ج
    1.13
    POSITIVE LOGITS
    -
    1.23
    "
    1.16
     I
    1.14
    B
    1.14
    ל
    1.07
    A
    1.06
    nosti
    1.04
    '
    1.00
    C
    1.00
     R
    0.99
    Act Density 0.000%

    No Known Activations