INDEX
    Explanations

    quotation marks

    New Auto-Interp
    Negative Logits
     captain
    -0.08
     Merlin
    -0.08
     Pat
    -0.07
     sucking
    -0.07
    мон
    -0.07
     Powers
    -0.07
     christ
    -0.07
    umers
    -0.07
     Ane
    -0.07
     kako
    -0.07
    POSITIVE LOGITS
    お願い
    0.08
    お願
    0.08
     encouraged
    0.08
    ეჭ
    0.07
     retr
    0.07
     kawai
    0.07
     instructed
    0.07
     rejoice
    0.07
     בעבר
    0.07
     serious
    0.07
    Act Density 0.036%

    No Known Activations