INDEX
Explanations
possessive pronouns referring to a collective group
occurrences of the word "Their"
New Auto-Interp
Negative Logits
Ïĥ
-0.67
κ
-0.67
react
-0.66
rouse
-0.66
que
-0.64
cloth
-0.63
DR
-0.61
ige
-0.61
QL
-0.60
select
-0.58
POSITIVE LOGITS
selves
0.93
Own
0.92
terness
0.92
self
0.88
resy
0.87
Costs
0.87
Differences
0.85
Tracks
0.81
Latest
0.81
Approach
0.78
Activations Density 0.021%