INDEX
Explanations
prepositions and their relationships in a sentence
New Auto-Interp
Head Attr Weights
0:0.02
1:0.03
2:0.08
3:0.08
4:0.10
5:0.04
6:0.05
7:0.28
8:0.03
9:0.05
10:0.12
11:0.07
Negative Logits
Laun
-1.45
�
-1.45
ocide
-1.37
vis
-1.37
laughter
-1.36
FontSize
-1.31
disse
-1.28
slic
-1.22
topp
-1.21
conquering
-1.19
POSITIVE LOGITS
Trinidad
1.39
ividually
1.29
bler
1.28
etitive
1.26
Swan
1.24
blers
1.22
endi
1.21
artment
1.21
Huma
1.21
Alto
1.20
Activations Density 0.165%