INDEX
Explanations
instances of personal conflicts or grievances
expressions of personal grievances and inquiries about wrongdoing
New Auto-Interp
Negative Logits
tnc
-0.60
odge
-0.59
doi
-0.57
currently
-0.55
inline
-0.55
rouse
-0.54
idi
-0.53
ipher
-0.52
FIG
-0.52
cellaneous
-0.52
POSITIVE LOGITS
terday
0.91
yesterday
0.86
?",
0.78
BEFORE
0.78
?'
0.75
!?
0.75
ago
0.72
?!
0.71
?!"
0.70
?"
0.70
Activations Density 0.789%