INDEX
    Explanations

    names of actors and directors in a film context

    New Auto-Interp
    Negative Logits
    -space
    -0.15
    culo
    -0.14
    gateway
    -0.14
    isas
    -0.14
    haps
    -0.14
     gap
    -0.14
    lice
    -0.13
     NhÃł
    -0.13
    rase
    -0.13
    ury
    -0.13
    POSITIVE LOGITS
    tuÄŁ
    0.17
    -addons
    0.17
    ijken
    0.16
    ovice
    0.14
    ureau
    0.14
    rog
    0.14
    )[-
    0.13
    -ignore
    0.13
    ì°¬
    0.13
     Ñģло
    0.13
    Act Density 0.019%

    No Known Activations