INDEX
Explanations
phrases related to legal responsibility and negligence
New Auto-Interp
Negative Logits
keh
-0.16
ilip
-0.15
313
-0.14
escort
-0.14
avid
-0.14
ÑĢим
-0.14
cheid
-0.14
ckill
-0.14
erties
-0.13
Grinder
-0.13
POSITIVE LOGITS
responsible
0.40
causing
0.33
cause
0.33
causes
0.32
Responsible
0.32
ponsible
0.29
caus
0.29
contributing
0.28
Cause
0.28
responsable
0.27
Activations Density 0.229%