INDEX
    Explanations

    a followed by punctuation

    New Auto-Interp
    Negative Logits
    𝘵
    2.19
    mainan
    2.11
     äußerst
    2.02
    2.02
    ssa
    1.97
    gewicht
    1.95
    gruppe
    1.88
    د
    1.87
    ました
    1.86
    یر
    1.85
    POSITIVE LOGITS
     través
    1.72
    ב
    1.66
     memoir
    1.63
     tinge
    1.58
    ida
    1.55
    ной
    1.55
    1.55
     benefactor
    1.52
     vote
    1.50
     monograph
    1.48
    Act Density 0.390%

    No Known Activations