INDEX
Explanations
statements or references to donations and fundraising activities
Tokens following punctuation or symbols
social media symbols and quotes
New Auto-Interp
Negative Logits
*/;
-1.00
–,
-0.92
>");
-0.91
")));
-0.91
"},
-0.85
".
-0.84
</caption>
-0.84
')));
-0.83
]';
-0.81
'));
-0.81
POSITIVE LOGITS
#
2.39
@
1.99
#
1.81
@
1.39
\#
1.39
.#
1.27
(@
1.23
:#
1.20
(#
1.17
(@
1.17
Activations Density 0.168%