INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     incrível
    -0.88
     burger
    -0.81
     sandwiches
    -0.80
     mechanical
    -0.78
    bigli
    -0.78
     MECHANICAL
    -0.77
    tacos
    -0.77
     greenish
    -0.77
    Tacos
    -0.77
    inven
    -0.76
    POSITIVE LOGITS
    Koordinaten
    0.86
    ívne
    0.84
     adaptations
    0.82
     折りたたみ
    0.82
     isomorphism
    0.81
    ")]
    0.80
    tivities
    0.80
    }")
    0.79
     Δ
    0.79
    tamine
    0.79
    Act Density 0.010%

    No Known Activations