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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    1
    1.31
    la
    1.20
    ino
    1.06
    in
    1.02
    r
    1.01
    m
    0.94
    to
    0.93
    re
    0.90
    f
    0.90
    。
    0.90
    POSITIVE LOGITS
    ل
    1.50
    ת
    1.41
    S
    1.34
    C
    1.34
    т
    1.34
    З
    1.31
    л
    1.30
    К
    1.29
    스
    1.27
    ة
    1.26
    Act Density 0.000%

    No Known Activations