INDEX
Explanations
references to the color blue, especially in varying contexts
mentions of "Blue"
New Auto-Interp
Negative Logits
complexContent
-0.78
Италијани
-0.64
Παραπομπές
-0.58
exitRule
-0.56
tagHelperRunner
-0.56
invokingState
-0.54
empêcher
-0.53
selaer
-0.52
Numerade
-0.52
duquel
-0.52
POSITIVE LOGITS
Blue
0.84
BLUE
0.84
BLUE
0.81
Blue
0.81
aarrggbb
0.80
Blu
0.76
blu
0.75
blue
0.74
blue
0.73
blu
0.73
Activations Density 0.051%