INDEX
Explanations
mentions of the organization Amnesty International
references to Amnesty International and the concept of amnesty
New Auto-Interp
Negative Logits
hatt
-0.68
umber
-0.66
ests
-0.65
ottesville
-0.65
iership
-0.64
orned
-0.64
omal
-0.64
istic
-0.64
Ń·
-0.64
ropy
-0.64
POSITIVE LOGITS
mble
0.77
lda
0.73
Byrne
0.65
ij士
0.62
CTR
0.62
Dign
0.62
vor
0.61
2021
0.60
pered
0.60
men
0.59
Activations Density 0.094%