INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -0.08
     Burger
    -0.07
    kind
    -0.07
     anch
    -0.07
     degr
    -0.07
    -0.07
    emb
    -0.07
     lag
    -0.07
     anchored
    -0.06
     anchor
    -0.06
    POSITIVE LOGITS
    daki
    0.08
     אב
    0.08
    0.08
    ürde
    0.08
    0.08
    /topic
    0.08
    0.08
     lọ
    0.08
    Qualifier
    0.08
    0.07
    Act Density 0.008%

    No Known Activations