INDEX
    Explanations

    references to ice cream or its variations in the text

    New Auto-Interp
    Negative Logits
    ši
    -0.16
    ëļ
    -0.16
    cott
    -0.15
    etter
    -0.14
     mũi
    -0.14
    cyan
    -0.14
    ì¢ħ
    -0.14
     Ward
    -0.14
    Ł
    -0.14
    asant
    -0.13
    POSITIVE LOGITS
     cream
    0.56
    cre
    0.51
     Cream
    0.48
    CRE
    0.47
    cream
    0.46
     cre
    0.45
    Cream
    0.42
    Cre
    0.42
     Cre
    0.41
     creams
    0.40
    Act Density 0.018%

    No Known Activations