INDEX
Explanations
abbreviations and company names
New Auto-Interp
Negative Logits
«
-0.18
"↵
-0.15
''↵
-0.14
``
-0.14
«
-0.14
\"
-0.14
'',
-0.14
""↵
-0.14
"
-0.14
\"",
-0.13
POSITIVE LOGITS
.'
0.46
.’
0.44
]'
0.39
)'
0.39
>'
0.36
.'
0.36
!'
0.35
}'
0.35
?'
0.35
!’
0.34
Activations Density 0.080%