INDEX
Explanations
words related to blaming someone for something
references to blame and the act of blaming others
New Auto-Interp
Negative Logits
tein
-0.89
intend
-0.74
ierre
-0.73
intage
-0.68
steel
-0.67
isode
-0.67
andowski
-0.67
efer
-0.67
naissance
-0.66
adiator
-0.66
POSITIVE LOGITS
blame
1.03
scapego
0.85
sclerosis
0.75
blaming
0.75
squarely
0.73
blames
0.72
faulty
0.71
inaction
0.68
errors
0.68
fault
0.68
Activations Density 0.042%