INDEX
Explanations
expressions of fear and danger in personal testimonies
New Auto-Interp
Negative Logits
бÑĥдÑĮ
-0.17
dma
-0.17
Äįi
-0.15
bakan
-0.15
acid
-0.15
iry
-0.14
baÅŁta
-0.14
quelle
-0.14
sans
-0.13
obec
-0.13
POSITIVE LOGITS
maybe
0.20
here
0.18
lots
0.16
like
0.16
big
0.15
very
0.15
maybe
0.15
like
0.15
[s
0.15
always
0.14
Activations Density 0.282%