INDEX
Explanations
phrases related to trending topics or news on social media platforms
occurrences of the word "trending" and its variations
New Auto-Interp
Negative Logits
porting
-0.78
rique
-0.76
rehens
-0.69
esville
-0.69
̶
-0.68
alin
-0.66
udd
-0.66
aments
-0.65
vette
-0.65
aer
-0.65
POSITIVE LOGITS
Trend
1.07
Trend
1.04
trending
1.03
trend
0.88
hasht
0.87
trends
0.85
ĸļ
0.79
downwards
0.75
Trends
0.74
twe
0.72
Activations Density 0.008%