INDEX
Explanations
references to personal experiences and identities
contextual references to personal interests and experiences
New Auto-Interp
Negative Logits
emptory
-0.53
ettei
-0.51
enegger
-0.49
Ibid
-0.49
它
-0.49
彼らは
-0.49
sqcup
-0.48
him
-0.48
gazette
-0.47
它的
-0.46
POSITIVE LOGITS
Currently
0.90
currently
0.88
Currently
0.88
Actualmente
0.82
currently
0.81
actualmente
0.81
Born
0.72
Born
0.69
Been
0.69
Actualmente
0.68
Activations Density 0.088%