INDEX
    Explanations

    phrases that suggest similarity or comparison

    New Auto-Interp
    Negative Logits
    ing
    -0.47
     מדי
    -0.39
    -0.39
    rás
    -0.38
    MSB
    -0.37
     przedsiębior
    -0.36
    -0.36
    GB
    -0.35
     silo
    -0.35
     katze
    -0.34
    POSITIVE LOGITS
    styleType
    0.72
     CreateTagHelper
    0.64
    twimg
    0.62
     ModelExpression
    0.61
     klingt
    0.60
    afficheront
    0.59
    seemed
    0.59
    0.59
     feels
    0.59
     sounded
    0.59
    Act Density 0.166%

    No Known Activations