INDEX
Explanations
the mention of the term "Gren," likely referencing Grenfell Tower and its associated events or context
New Auto-Interp
Negative Logits
eum
-0.19
crow
-0.16
remium
-0.15
ppard
-0.15
cq
-0.15
asan
-0.15
essel
-0.14
omer
-0.14
amment
-0.14
apia
-0.14
POSITIVE LOGITS
oble
0.24
fell
0.22
ache
0.21
adier
0.19
inja
0.18
SPAN
0.18
Gren
0.18
velle
0.18
ada
0.18
ланд
0.17
Activations Density 0.004%