INDEX
Explanations
expressions of personal conflict or desire
New Auto-Interp
Negative Logits
therefore
-0.34
zwar
-0.29
indeed
-0.28
sice
-0.28
donc
-0.27
daher
-0.25
Therefore
-0.25
thus
-0.24
Therefore
-0.24
accordingly
-0.23
POSITIVE LOGITS
also
0.33
also
0.28
ALSO
0.28
Also
0.27
nevertheless
0.26
equally
0.25
nonetheless
0.25
åį»
0.25
Also
0.25
soon
0.25
Activations Density 0.598%