INDEX
Explanations
definite and indefinite articles along with some modifiers in descriptive phrases
New Auto-Interp
Negative Logits
beeld
-0.17
jay
-0.16
FC
-0.16
Unternehmen
-0.16
Thema
-0.15
label
-0.15
Leben
-0.15
Angebot
-0.15
heiten
-0.15
Antworten
-0.15
POSITIVE LOGITS
Minute
0.21
Phase
0.20
Serie
0.20
Palette
0.19
Episode
0.18
Pause
0.18
Rei
0.18
Sz
0.18
Situation
0.17
Eb
0.17
Activations Density 0.020%