INDEX
Explanations
id followed by type indicator
New Auto-Interp
Negative Logits
antigens
0.42
antibodies
0.41
Antibodies
0.39
apricot
0.39
grapefruit
0.38
alamat
0.37
molecules
0.37
capacitance
0.36
tense
0.36
mustered
0.36
POSITIVE LOGITS
empot
0.71
nummer
0.63
number
0.60
id
0.58
ID
0.53
号
0.51
id
0.48
ID
0.48
tid
0.48
é
0.48
Activations Density 0.022%