INDEX
Explanations
closing brackets in structured data
New Auto-Interp
Negative Logits
1
-0.67
i
-0.67
y
-0.65
le
-0.64
“
-0.63
3
-0.62
-
-0.61
-0.61
F
-0.61
of
-0.60
POSITIVE LOGITS
},
1.70
]},
1.54
"},
1.50
'},
1.46
},
1.46
.},
1.46
."),
1.42
)},
1.36
"}},
1.36
.],
1.35
Activations Density 0.194%