INDEX
    Explanations

    questions expressing disbelief or incredulity

    New Auto-Interp
    Negative Logits
    eniable
    -0.16
    nio
    -0.15
     Apprec
    -0.15
    111
    -0.15
    Locator
    -0.14
    enu
    -0.14
    emonic
    -0.14
    бе
    -0.14
    oyal
    -0.14
    itters
    -0.14
    POSITIVE LOGITS
     else
    0.23
     do
    0.20
    aya
    0.19
     timing
    0.18
     ELSE
    0.17
     say
    0.17
    else
    0.16
    	else
    0.16
     harm
    0.16
    Else
    0.16
    Act Density 0.070%

    No Known Activations