INDEX
Explanations
descriptive modifiers for concepts
New Auto-Interp
Negative Logits
sogenannten
1.12
Again
1.06
wiederum
1.05
wobei
1.03
And
1.01
The
1.01
again
1.01
the
1.00
Again
0.97
sogenannte
0.96
POSITIVE LOGITS
analogies
1.12
keywords
1.12
loopholes
1.10
metaphors
1.10
acronym
1.06
adjectives
1.06
abbreviations
1.03
taxonomic
1.02
subtitles
1.00
limitations
1.00
Activations Density 0.190%