INDEX
Explanations
mentions of social media and its associated impacts or uses in various contexts
New Auto-Interp
Negative Logits
angen
-0.16
elles
-0.15
iven
-0.15
eler
-0.14
resco
-0.14
genesis
-0.14
VML
-0.14
rray
-0.14
JD
-0.13
aja
-0.13
POSITIVE LOGITS
overall
0.20
yg
0.16
general
0.15
teng
0.15
inf
0.15
isin
0.14
other
0.14
ãģĵãģĨ
0.14
Mid
0.14
kova
0.14
Activations Density 0.305%