INDEX
Explanations
words related to medical conditions, particularly serious illnesses
references to illness and medical conditions
New Auto-Interp
Negative Logits
compr
-0.78
pees
-0.75
bloc
-0.71
ogle
-0.68
ramid
-0.67
zees
-0.66
bumper
-0.65
reme
-0.61
de
-0.61
cycl
-0.61
POSITIVE LOGITS
illness
0.89
outbreaks
0.89
outbreak
0.86
illnesses
0.84
ousing
0.82
plag
0.80
ochond
0.78
onset
0.77
symptoms
0.76
Symptoms
0.75
Activations Density 0.014%