INDEX
Explanations
instances of events or activities where people gather publicly for a specific purpose
occurrences of the word "demonstration" and its variations
New Auto-Interp
Negative Logits
laus
-0.77
efe
-0.70
ecd
-0.70
paste
-0.69
saline
-0.67
seed
-0.66
oho
-0.66
lake
-0.65
learn
-0.64
label
-0.63
POSITIVE LOGITS
demonstration
0.87
GOODMAN
0.84
ary
0.80
ista
0.79
antes
0.79
demonstrators
0.78
stration
0.78
arily
0.78
emonium
0.77
demonstrations
0.76
Activations Density 0.019%