INDEX
    Explanations

    sentence-ending punctuation marks, particularly periods and question marks

    New Auto-Interp
    Negative Logits
     Hatch
    -0.15
    van
    -0.15
    виÑĤ
    -0.15
     Lau
    -0.15
    pest
    -0.14
     Pare
    -0.14
     Globe
    -0.14
    lik
    -0.14
     vid
    -0.13
     Setup
    -0.13
    POSITIVE LOGITS
    335
    0.16
    createFrom
    0.16
    ephir
    0.15
    alles
    0.15
    olist
    0.15
    ieber
    0.14
    WSC
    0.14
    bsp
    0.14
    ħ
    0.14
    å¹³
    0.14
    Act Density 0.001%

    No Known Activations