INDEX
Explanations
references to numerical enumerations within square brackets, likely indicating citations or references in a text
references to numerical data or statistics
New Auto-Interp
Negative Logits
anooga
-0.65
contag
-0.65
unemploy
-0.64
cooperative
-0.62
whiff
-0.61
positively
-0.61
)))
-0.60
unemployment
-0.59
modelling
-0.57
baking
-0.57
POSITIVE LOGITS
][
1.63
]
1.61
]"
1.49
],[
1.35
]'
1.30
]}
1.29
].
1.29
]:
1.20
],
1.19
])
1.17
Activations Density 0.033%