INDEX
Explanations
concepts related to justice and fairness in social issues
Text preceding end quotation marks
end of sentence punctuation
New Auto-Interp
Negative Logits
'),
-1.80
'],
-1.80
"],
-1.76
'])
-1.74
']);
-1.72
"])
-1.68
"),
-1.68
'))
-1.67
'):
-1.67
"]);
-1.62
POSITIVE LOGITS
."
0.87
।
0.77
.”
0.73
.</
0.62
.)
0.58
。
0.52
.,
0.49
ั้ง
0.46
↵↵↵
0.45
↵↵
0.45
Activations Density 0.230%