INDEX
Explanations
mathematical expressions or notation
$\mathbb{C}^{2}$
New Auto-Interp
Negative Logits
)
-0.52
”)
-0.46
),
-0.46
),
-0.44
”),
-0.43
})}
-0.42
"),
-0.41
)
-0.40
’)
-0.40
)}
-0.39
POSITIVE LOGITS
}^{1.53
^{1.17
|^{1.05
\}^{1.03
)}^{1.03
^{0.94
]^{0.93
}}^{0.93
}}^{0.92
$^{0.92
Activations Density 0.115%