INDEX
Explanations
calls to action or prompts for user interaction
New Auto-Interp
Negative Logits
bezeichneter
-0.79
{{$-0.70
warden
-0.69
">{{$-0.69
">{{-0.68
BoxDecoration
-0.68
<thead>
-0.68
Bowl
-0.65
;;;
-0.65
}`}>
-0.64
POSITIVE LOGITS
CLICK
1.39
clicks
1.37
CLICK
1.25
Clicks
1.21
clicks
1.18
click
1.17
Click
1.16
clicked
1.15
clicking
1.15
Klick
1.13
Activations Density 0.051%