INDEX
Explanations
references to individuals and their roles or actions within a societal or historical context
"who" followed by a verb
who followed by verb
New Auto-Interp
Negative Logits
()]);
-0.89
незавершена
-0.87
=?";
-0.82
"}")
-0.82
متعلقه
-0.81
"]);
-0.72
']],
-0.70
]++;
-0.69
]
-0.69
"])
-0.69
POSITIVE LOGITS
while
1.51
during
1.47
despite
1.46
after
1.46
although
1.39
whilst
1.35
when
1.27
since
1.23
despite
1.18
during
1.16
Activations Density 0.408%