INDEX
Explanations
references to the term "cool" in various contexts
New Auto-Interp
Negative Logits
instructed
-0.47
tramonto
-0.46
__':
-0.45
windowFixed
-0.44
ValueStyle
-0.44
ſelves
-0.42
cop
-0.41
predicted
-0.40
ſent
-0.40
setAccessible
-0.40
POSITIVE LOGITS
coolness
0.74
Cool
0.72
Cool
0.72
cool
0.66
kudos
0.58
coolest
0.57
Awesome
0.57
cool
0.56
COOL
0.56
cools
0.54
Activations Density 0.179%