INDEX
Explanations
references to doors and their states (open, closed, locked)
a "door" or "doors"
doors opening or closing
New Auto-Interp
Negative Logits
)]$
-0.67
]){
-0.66
]--;
-0.64
^)
-0.63
")));
-0.61
--
-0.61
quanto
-0.61
$")
-0.61
")),
-0.60
%]
-0.60
POSITIVE LOGITS
doors
1.42
door
1.39
door
1.29
DOOR
1.27
Door
1.25
Doors
1.22
Doors
1.21
Door
1.19
doors
1.14
DOOR
1.05
Activations Density 0.093%