INDEX
    Explanations

    conversational phrases and expressions of opinion

    New Auto-Interp
    Negative Logits
    ↵↵
    -0.50
    2
    -0.49
     distanciation
    -0.48
    1
    -0.48
    han
    -0.46
    𝐃
    -0.45
    :
    -0.45
    と思い
    -0.45
    рий
    -0.44
     Opiniones
    -0.43
    POSITIVE LOGITS
    󠁿
    0.80
    }{*}{}
    0.77
    inthians
    0.72
    "]();
    0.72
    NUMX
    0.72
     transfieras
    0.71
    SharedDtor
    0.71
    endphp
    0.70
    ScopeManager
    0.70
    `,
    
    0.69
    Act Density 0.288%

    No Known Activations