INDEX
Explanations
actors and objects interacting
New Auto-Interp
Negative Logits
containing
0.37
Understanding
0.35
containing
0.35
contenant
0.35
intended
0.34
Contain
0.33
taken
0.33
Jann
0.33
chromatography
0.33
angeboten
0.33
POSITIVE LOGITS
vying
0.76
participating
0.67
terlibat
0.65
inhabiting
0.63
doing
0.62
ktorí
0.61
enjoying
0.61
performing
0.60
competing
0.58
interacting
0.58
Activations Density 0.031%