INDEX
Explanations
expressions related to personal loss and emotional struggles
New Auto-Interp
Negative Logits
}.
-0.83
".
-0.82
)}$.
-0.78
).
-0.78
}.
-0.75
).}
-0.75
()).
-0.74
'].
-0.73
}).
-0.71
"").
-0.71
POSITIVE LOGITS
,”
2.39
,"
2.03
,”
1.80
,’’
1.59
,''
1.58
,’
1.50
,'
1.45
),”
1.45
,“
1.45
.,"
1.34
Activations Density 0.490%