INDEX
Explanations
mathematical or logical symbols
Mathematical or code snippets with symbols
mathematical notation with braces
New Auto-Interp
Negative Logits
ly
-0.81
iſt
-0.77
Eſ
-0.77
Reſ
-0.75
Anſ
-0.74
ſub
-0.71
ſy
-0.71
doubtnut
-0.68
ROY
-0.66
Inſ
-0.65
POSITIVE LOGITS
}}$
1.05
)}$
1.02
}}$,
0.99
}\}$
0.96
$)$
0.93
]$}
0.90
}}$.
0.90
)\}$
0.89
EconPapers
0.87
)$}
0.86
Activations Density 0.618%