INDEX
Explanations
references to breast cancer cell lines and their characteristics
New Auto-Interp
Negative Logits
tekem
-0.65
Carne
-0.57
matorium
-0.53
mundo
-0.53
mock
-0.52
kautta
-0.51
kör
-0.50
uremberg
-0.49
מת
-0.48
Pov
-0.48
POSITIVE LOGITS
MB
1.44
MB
1.28
MT
1.21
MT
1.18
MF
1.16
MW
1.16
MM
1.10
MH
1.09
MN
1.09
MN
1.08
Activations Density 0.178%