INDEX
Explanations
mentions of a specific course or program labeled "CS 9" or similar
references to computer science courses or topics
New Auto-Interp
Negative Logits
ously
-0.82
zzi
-0.67
Mandela
-0.64
fitted
-0.62
Hearts
-0.62
erers
-0.61
iating
-0.61
ishly
-0.60
Pharaoh
-0.60
atively
-0.59
POSITIVE LOGITS
IRO
1.08
RF
0.99
MX
0.90
GO
0.89
DP
0.88
hent
0.86
DN
0.83
WER
0.82
CEPT
0.80
MC
0.80
Activations Density 0.039%